Security Codex plugins

Publisher keywords · listing

security code-review diff-review appsec threat-modeling

Publisher full description

…e official, community or unknown, how they run, what they can reach, and how many devices use them. Work the allowlist. See what is waiting for approval across AI tools, AI sites, model providers, MCP servers, extensions, plugins and skills. Admins can approve the items they confirm, when an owner has turned that on in Anomity Settings. Audit changes and compliance. Ask what ch…

Publisher description

…, Microsoft Copilot, ChatGPT or any MCP-compatible client) to the Ansvar Gateway and run compliance work directly in that assistant: regulatory gap analyses, threat models (STRIDE/LINDDUN, TARA), DPIAs and audit preparation, grounded in more than 300 curated corpora of EU and international legislation, case law, preparatory works, regulator guidance and security…

Publisher full description

…own hardware, plus answers about ArrowMem's privacy design. You can check whether your self-hosted model server is reachable from outside your machine, check whether it still matches the hardening guide, read the live-tested hardening procedure itself, and list the AI tools configured on your machi… …and date. A security alert relay can also send a push notice to you or your family. The check tools work only from diagnostic output you paste; they do not connect to your machine or network.

Publisher full description

Inspect repository policy, GitHub Actions trust boundaries, and moderation automation without network access or repository mutation; generate reviewable remediation patches on request.

Publisher full description

Use Custodis Token mode in three steps: Add document, Check & share, Use answer. It automatically replaces detected private details with tokens on your device. Review the exact text, approve it, then send it to ChatGPT. Paste the reply into the same open workspace to restore the real details locally. Review private details and consistent tokens side by side. Click an original value to hide or show it locally while keeping it protected. Click the red ×…

Publisher full description

…uides a step-by-step security scan of Python code with the open-source Frame command-line tool. The workflow checks that the Frame CLI is installed (and points you to the README install steps if it is not, without installing anything itself), runs frame scan, optionally adds the AI layer through a c… …fidence. It separates symbolic findings, which the Frame README describes as proven reachable, from model-only findings that are leads to check. It then triages false positives, proposes fixes with frame fix as a diff for you to review, changes files only after you agree, and re-scans to confirm. Be…

Publisher full description

…s. - Discover: find unregistered lookalikes of a domain that could still be registered defensively. Work your organization's detections - Query: search lookalikes found for your monitored domains, and Email Intelligence and Site Canary events, from the last 30 days. The model reads the field catalog before writing a query, so you can ask in plain language. - Alerts: review the alerts your detection rules raised, the evidence each cites and whether each response reach…

Publisher description

…ns every asset, alert, identity, and dependency is already stitched together in Orca’s Unified Data Model before users ask a question. Every answer factors in reachability, blast radius, and business impact from the first response. For teams that want the reasoning without writing the prompts, Orca… …ork it, modify it, and extend it to their own use cases. The result: security and engineering teams work across cloud, code, and AI from a single workspace, with Orca's reasoning behind every answer.

Publisher full description

…s a command-line security scanner for AI coding sessions. The audit skill, skarn-audit, teaches the model to run the skarn CLI on this machine and act on what it reports. The skill runs two passes. skarn assess reads the session transcripts that AI coding assistants have already written to disk and… …n remote code or send data off the machine. Both passes run entirely on this machine and make no network call. Neither modifies a session transcript or a configuration file, and every credential value in the output is masked, so a finding names a rule and a masked preview and never the credential it…

Publisher full description

Review applications with an evidence-first security workflow that maps attack surfaces, tests authentication and access controls, traces dangerous inputs, models threats, and verifies fixes.