Update to Codex Security
Snapshot Nov 18, 2026 · 06:12 UTC · version 0.1.33
Collection source: downloaded plugin package. These snapshots do not have a confirmed matching collection source. Differences in file lists alone do not establish changes to the package.
Instructions updated for verify-fix
Skill instructions — Now says: format. Use `standard` verification unless the caller explicitly selects `verificationMode: static`. In static mode, assess the current source and diff, the...
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 3 plugins free · no card required.
All fields and original values.
Skill instructions
Sep 30, 2026 · 23:19 UTC
format without applying this skill's JSON result contract. 4. Run the original reproducer, focused regression checks, or legitimate-behavior checks only when they can run without modifying the repository. Preserve exact static evidence w...
Nov 18, 2026 · 06:12 UTC
format. Use `standard` verification unless the caller explicitly selects `verificationMode: static`. In static mode, assess the current source and diff, the original exploit path and plausible bypasses, and legitimate behavior through ca...
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -7,7 +7,7 @@ ## When to Use -Invoke this skill only for an explicit request to verify a security fix, including a direct `$verify-fix` invocation. A request to implement a fix or run its tests does not by itself request this skill. For other tasks, follow the user's requested workflow and response format without applying this skill's JSON result contract. +Invoke this skill only for an explicit request to verify a security fix, including a direct `$verify-fix` invocation. A request to implement a fix or run its tests does not by itself request this skill. For other tasks, follow the user's requested workflow and response format. ## Objective @@ -17,17 +17,21 @@ Use `../../references/static-finding-assessment.md` to identify the original attacker-controlled source, security control, sensitive sink, reachable path, trust boundary, counterevidence, and proof gaps. If the caller already supplied that reference in the prompt, use the supplied contents without reading it again. +Use `standard` verification unless the caller explicitly selects `verificationMode: static`. In static mode, assess the current source and diff, the original exploit path and plausible bypasses, and legitimate behavior through callers and existing tests read as source. Do not install dependencies or run builds, tests, reproducers, or the application, including when validation instructions request them. Repository-reading tools remain available. State in the evidence that this is a static assessment and runtime checks were not performed; do not count them as passed or require them for this assessment. Missing runtime tooling alone does not make the result inconclusive, but a material gap in the source evidence does. + ## Verification Workflow 1. Establish the original vulnerability, its preconditions, affected security boundary, and legitimate behavior that must continue to work. 2. Confirm the current checkout contains the affected component. Follow moved or refactored code rather than treating a missing file, removed line, or changed function name as proof of remediation. 3. Trace the original exploit path through the current implementation and check the nearest relevant control, equivalent paths, and plausible bypasses. -4. Run the original reproducer, focused regression checks, or legitimate-behavior checks only when they can run without modifying the repository. Preserve exact static evidence when runtime checks are unavailable. +4. In standard mode, run the original reproducer, focused regression checks, or legitimate-behavior checks only when they can run without modifying the repository. Preserve exact static evidence when runtime checks are unavailable. 5. Return one result per supplied finding, in the requested order. Treat closed tickets, unrelated passing tests, and the absence of a new scan finding as insufficient proof. ## Result Contract -Return exactly one JSON object: +For interactive conversations, use readable Markdown unless the caller requests another format. Give a verdict for each finding, explain the supporting evidence with source references, and identify relevant checks and remaining proof gaps. + +When the caller requests JSON or supplies an automated result contract, return exactly one JSON object in this shape. CLI verification workflows explicitly request this contract. Use the same verdicts and evidence requirements in either format. ```json { @@ -43,6 +47,6 @@ - Use `fixed` only when evidence proves the original security boundary is closed and legitimate behavior remains intact. - Use `still_vulnerable` only when evidence proves the original vulnerable path remains reachable. -- Use `inconclusive` for a repository mismatch, missing original context, unavailable relevant checks, an unproven legitimate control, or another material proof gap. +- Use `inconclusive` for a repository mismatch, missing original context, unavailable checks required by the selected mode, an unproven legitimate control, or another material proof gap. Never infer a stronger verdict by weakening the read-only boundary, substituting a different vulnerability, or hiding missing evidence.
Full technical diff · 1 changed fields
changed /skill_md_contents
"---\nname: verify-fix\ndescription: Use only when the user explicitly requests verification that a security fix remediates a reported vulnerability. Do not invoke automatically while implementing fixes, reviewing ordinary code changes, or running tests. Do not use for non-security fixes, candidate finding validation, or full repository scans.\n---\n\n# Verify Fix\n\n## When to Use\n\nInvoke this skill only for an explicit request to verify a security fix, including a direct `$verify-fix` invocation. A request to implement a fix or run its tests does not by itself request this skill. For other tasks, follow the user's requested workflow and response format without applying this skill's JSON result contract.\n\n## Objective\n\nDetermine whether each supplied security finding has been fixed in the current checkout. Operate in standalone verification-only mode; do not create, modify, or delete repository files, apply patches, commit changes, write artifacts, or modify issue trackers.\n\n## Assessment Method\n\nUse `../../references/static-finding-assessment.md` to identify the original attacker-controlled source, security control, sensitive sink, reachable path, trust boundary, counterevidence, and proof gaps. If the caller already supplied that reference in the prompt, use the supplied contents without reading it again.\n\n## Verification Workflow\n\n1. Establish the original vulnerability, its preconditions, affected security boundary, and legitimate behavior that must continue to work.\n2. Confirm the current checkout contains the affected component. Follow moved or refactored code rather than treating a missing file, removed line, or changed function name as proof of remediation.\n3. Trace the original exploit path through the current implementation and check the nearest relevant control, equivalent paths, and plausible bypasses.\n4. Run the original reproducer, focused regression checks, or legitimate-behavior checks only when they can run without modifying the repository. Preserve exact static evidence when runtime checks are unavailable.\n5. Return one result per supplied finding, in the requested order. Treat closed tickets, unrelated passing tests, and the absence of a new scan finding as insufficient proof.\n\n## Result Contract\n\nReturn exactly one JSON object:\n\n```json\n{\n \"results\": [\n {\n \"id\": \"finding-or-issue-id\",\n \"status\": \"fixed|still_vulnerable|inconclusive\",\n \"evidence\": \"specific current source, exploit, test, or proof-gap evidence\"\n }\n ]\n}\n```\n\n- Use `fixed` only when evidence proves the original security boundary is closed and legitimate behavior remains intact.\n- Use `still_vulnerable` only when evidence proves the original vulnerable path remains reachable.\n- Use `inconclusive` for a repository mismatch, missing original context, unavailable relevant checks, an unproven legitimate control, or another material proof gap.\n\nNever infer a stronger verdict by weakening the read-only boundary, substituting a different vulnerability, or hiding missing evidence.\n""---\nname: verify-fix\ndescription: Use only when the user explicitly requests verification that a security fix remediates a reported vulnerability. Do not invoke automatically while implementing fixes, reviewing ordinary code changes, or running tests. Do not use for non-security fixes, candidate finding validation, or full repository scans.\n---\n\n# Verify Fix\n\n## When to Use\n\nInvoke this skill only for an explicit request to verify a security fix, including a direct `$verify-fix` invocation. A request to implement a fix or run its tests does not by itself request this skill. For other tasks, follow the user's requested workflow and response format.\n\n## Objective\n\nDetermine whether each supplied security finding has been fixed in the current checkout. Operate in standalone verification-only mode; do not create, modify, or delete repository files, apply patches, commit changes, write artifacts, or modify issue trackers.\n\n## Assessment Method\n\nUse `../../references/static-finding-assessment.md` to identify the original attacker-controlled source, security control, sensitive sink, reachable path, trust boundary, counterevidence, and proof gaps. If the caller already supplied that reference in the prompt, use the supplied contents without reading it again.\n\nUse `standard` verification unless the caller explicitly selects `verificationMode: static`. In static mode, assess the current source and diff, the original exploit path and plausible bypasses, and legitimate behavior through callers and existing tests read as source. Do not install dependencies or run builds, tests, reproducers, or the application, including when validation instructions request them. Repository-reading tools remain available. State in the evidence that this is a static assessment and runtime checks were not performed; do not count them as passed or require them for this assessment. Missing runtime tooling alone does not make the result inconclusive, but a material gap in the source evidence does.\n\n## Verification Workflow\n\n1. Establish the original vulnerability, its preconditions, affected security boundary, and legitimate behavior that must continue to work.\n2. Confirm the current checkout contains the affected component. Follow moved or refactored code rather than treating a missing file, removed line, or changed function name as proof of remediation.\n3. Trace the original exploit path through the current implementation and check the nearest relevant control, equivalent paths, and plausible bypasses.\n4. In standard mode, run the original reproducer, focused regression checks, or legitimate-behavior checks only when they can run without modifying the repository. Preserve exact static evidence when runtime checks are unavailable.\n5. Return one result per supplied finding, in the requested order. Treat closed tickets, unrelated passing tests, and the absence of a new scan finding as insufficient proof.\n\n## Result Contract\n\nFor interactive conversations, use readable Markdown unless the caller requests another format. Give a verdict for each finding, explain the supporting evidence with source references, and identify relevant checks and remaining proof gaps.\n\nWhen the caller requests JSON or supplies an automated result contract, return exactly one JSON object in this shape. CLI verification workflows explicitly request this contract. Use the same verdicts and evidence requirements in either format.\n\n```json\n{\n \"results\": [\n {\n \"id\": \"finding-or-issue-id\",\n \"status\": \"fixed|still_vulnerable|inconclusive\",\n \"evidence\": \"specific current source, exploit, test, or proof-gap evidence\"\n }\n ]\n}\n```\n\n- Use `fixed` only when evidence proves the original security boundary is closed and legitimate behavior remains intact.\n- Use `still_vulnerable` only when evidence proves the original vulnerable path remains reachable.\n- Use `inconclusive` for a repository mismatch, missing original context, unavailable checks required by the selected mode, an unproven legitimate control, or another material proof gap.\n\nNever infer a stronger verdict by weakening the read-only boundary, substituting a different vulnerability, or hiding missing evidence.\n"Full snapshot data
{
"description": "Use only when the user explicitly requests verification that a security fix remediates a reported vulnerability. Do not invoke automatically while implementing fixes, reviewing ordinary code changes, or running tests. Do not use for non-security fixes, candidate finding validation, or full repository scans.",
"included_files": [
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 235
}
],
"name": "verify-fix",
"skill_md_contents": "---\nname: verify-fix\ndescription: Use only when the user explicitly requests verification that a security fix remediates a reported vulnerability. Do not invoke automatically while implementing fixes, reviewing ordinary code changes, or running tests. Do not use for non-security fixes, candidate finding validation, or full repository scans.\n---\n\n# Verify Fix\n\n## When to Use\n\nInvoke this skill only for an explicit request to verify a security fix, including a direct `$verify-fix` invocation. A request to implement a fix or run its tests does not by itself request this skill. For other tasks, follow the user's requested workflow and response format.\n\n## Objective\n\nDetermine whether each supplied security finding has been fixed in the current checkout. Operate in standalone verification-only mode; do not create, modify, or delete repository files, apply patches, commit changes, write artifacts, or modify issue trackers.\n\n## Assessment Method\n\nUse `../../references/static-finding-assessment.md` to identify the original attacker-controlled source, security control, sensitive sink, reachable path, trust boundary, counterevidence, and proof gaps. If the caller already supplied that reference in the prompt, use the supplied contents without reading it again.\n\nUse `standard` verification unless the caller explicitly selects `verificationMode: static`. In static mode, assess the current source and diff, the original exploit path and plausible bypasses, and legitimate behavior through callers and existing tests read as source. Do not install dependencies or run builds, tests, reproducers, or the application, including when validation instructions request them. Repository-reading tools remain available. State in the evidence that this is a static assessment and runtime checks were not performed; do not count them as passed or require them for this assessment. Missing runtime tooling alone does not make the result inconclusive, but a material gap in the source evidence does.\n\n## Verification Workflow\n\n1. Establish the original vulnerability, its preconditions, affected security boundary, and legitimate behavior that must continue to work.\n2. Confirm the current checkout contains the affected component. Follow moved or refactored code rather than treating a missing file, removed line, or changed function name as proof of remediation.\n3. Trace the original exploit path through the current implementation and check the nearest relevant control, equivalent paths, and plausible bypasses.\n4. In standard mode, run the original reproducer, focused regression checks, or legitimate-behavior checks only when they can run without modifying the repository. Preserve exact static evidence when runtime checks are unavailable.\n5. Return one result per supplied finding, in the requested order. Treat closed tickets, unrelated passing tests, and the absence of a new scan finding as insufficient proof.\n\n## Result Contract\n\nFor interactive conversations, use readable Markdown unless the caller requests another format. Give a verdict for each finding, explain the supporting evidence with source references, and identify relevant checks and remaining proof gaps.\n\nWhen the caller requests JSON or supplies an automated result contract, return exactly one JSON object in this shape. CLI verification workflows explicitly request this contract. Use the same verdicts and evidence requirements in either format.\n\n```json\n{\n \"results\": [\n {\n \"id\": \"finding-or-issue-id\",\n \"status\": \"fixed|still_vulnerable|inconclusive\",\n \"evidence\": \"specific current source, exploit, test, or proof-gap evidence\"\n }\n ]\n}\n```\n\n- Use `fixed` only when evidence proves the original security boundary is closed and legitimate behavior remains intact.\n- Use `still_vulnerable` only when evidence proves the original vulnerable path remains reachable.\n- Use `inconclusive` for a repository mismatch, missing original context, unavailable checks required by the selected mode, an unproven legitimate control, or another material proof gap.\n\nNever infer a stronger verdict by weakening the read-only boundary, substituting a different vulnerability, or hiding missing evidence.\n"
}SHA-256 of public snapshot: 8d46e2860127ebe4d5913786dc142930f2451dd20783589097f3aec2eb4fe1a1