Update to AgentAvow
Snapshot Nov 19, 2026 · 01:02 UTC · version 1.1.3
Package or technical metadata updated
Package or technical metadata updated
Observed in package metadata. These changes alone do not establish a new customer-facing feature.
Up to 3 plugins free · no card required.
All fields and original values.
These are saved file metadata. Open a changed file to read its text edits.
Package file
Oct 24, 2026 · 13:48 UTC
c829d51862c7ad679f314dccda700579ed23e417ee7d3f9dcf0d13ec52d008ae
Nov 19, 2026 · 01:02 UTC
45146d42c27b2137c6f3aae8dc54df6e8e2d672276aafd46161f1d6ddbc43241
Package file
Oct 24, 2026 · 13:48 UTC
6475
Nov 19, 2026 · 01:02 UTC
6195
Compare saved observations
Download comparison JSONChanged files
Choose a file to see its text changes. Binary or large files show metadata only.
plugin.json
− removed · + added
--- before +++ after @@ -1,7 +1,7 @@ { "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json", "name": "agentavow", - "version": "1.1.2", + "version": "1.1.3", "description": "Scan an MCP server, package, or GitHub repo for a signed 0-100 trust score before your agent connects to it.", "author": { "name": "AgentAvow", @@ -22,7 +22,7 @@ "interface": { "displayName": "AgentAvow", "shortDescription": "Is this tool safe to connect?", - "longDescription": "AgentAvow tells you whether a tool is safe before your agent connects to it. Give it an MCP server, a package from npm, PyPI, crates or Docker, or a GitHub repo, and it answers in plain words: Safe to connect, Review before you connect, or Do not connect, with the reason. Underneath are two scores: a 0\u2013100 trust score, backed by a signed attestation anyone can recompute offline, and an adoption score built from real usage (downloads, stars, installs). It checks for known-malicious versions, published advisories, supply-chain and dependency risk, and code-safety issues, can run the tool in a sandbox to see what it actually does, and shows an interactive trust card. Eight read-only tools cover scanning a repo, package, or live MCP server; verifying a score; checking interaction safety before you connect; looking up an identity; and getting an embeddable badge. No account, no sign-in, and nothing is modified \u2014 every call is anonymous and read-only.", + "longDescription": "AgentAvow tells you whether a tool is safe before your agent connects to it. Give it an MCP server, a package from npm, PyPI, crates or Docker, or a GitHub repo, and it answers in plain words: Safe to connect, Review before you connect, or Do not connect, with the reason. It works in ChatGPT and in Codex: in Codex, ask about a server or package before you run codex mcp add or install it. Underneath are two scores: a 0\u2013100 trust score, backed by a signed attestation anyone can recompute offline, and an adoption score built from real usage (downloads, stars, installs). It checks for known-malicious versions, published advisories, supply-chain and dependency risk, and code-safety issues, can run the tool in a sandbox to see what it actually does, and shows an interactive trust card. Eight read-only tools cover scanning a repo, package, or live MCP server; verifying a score; checking interaction safety before you connect; looking up an identity; and getting an embeddable badge. No account, no sign-in, and nothing is modified \u2014 every call is anonymous and read-only.", "developerName": "Kenne Ives", "category": "Developer Tools", "capabilities": [ @@ -42,7 +42,7 @@ "logo": "./assets/logo.png" }, "publication": { - "release_notes": "Results now lead with one of three plain answers and the reason: Safe to connect, Review before you connect, or Do not connect, with the 0\u2013100 trust score and the adoption score underneath. Adds a bundled skill, scan-before-connect, that picks the right scan tool and reports the answer without overstating it; an output schema on the three scan tools so the structured result is described field by field; widget metadata on the trust card resource; and short status lines while a scan runs. A scan that cannot run now returns its guidance as a tool error. No tools were added or removed; all eight stay read-only." + "release_notes": "The listing now says how to use AgentAvow in Codex: ask about an MCP server or package before you run codex mcp add or install it. No tools were added, removed or changed; all eight stay read-only. The skill is unchanged." }, "review": { "test_cases": {
Full technical diff · 2 changed fields
changed /files/plugin.json/sha256
"c829d51862c7ad679f314dccda700579ed23e417ee7d3f9dcf0d13ec52d008ae"
"45146d42c27b2137c6f3aae8dc54df6e8e2d672276aafd46161f1d6ddbc43241"
changed /files/plugin.json/size
6475
6195
Full snapshot data
{
"files": {
".app.json": {
"sha256": "e2416f1a9fc62bd70e8329f6f3a2b95220a51d547003b51a3b3bbd6f29826547",
"size": 101
},
"assets/logo.png": {
"sha256": "084f427c6dc4a72b203765c0f3bf26e4aadf7250d8a78b1e2d59207ea413098f",
"size": 36643
},
"mcp.json": {
"sha256": "f044fdfe65a275e30dce519b157a2d6387e63225854c507f52ca1dbfd6e1921e",
"size": 197
},
"plugin.json": {
"sha256": "45146d42c27b2137c6f3aae8dc54df6e8e2d672276aafd46161f1d6ddbc43241",
"size": 6195
},
"skills/scan-before-connect/SKILL.md": {
"sha256": "0102d6dc97b6815aba961d39b7099f01dcf4e91a4e6143bac6d0f7148cd5f42b",
"size": 3583
},
"skills/scan-before-connect/agents/openai.yaml": {
"sha256": "b3196ea91032cefa9ff8950a4404a7137ce387b2d87bc3b727565d139ca30665",
"size": 189
}
}
}SHA-256 of public snapshot: f2429c2bb23477fc7d6e3fe64b67cf0f99e8398f140961577923359b311328c4