Security & Testing Agent Skills for OpenAI Agents SDK

Generate and run a coder-eval activation suite for a Claude Code skill.

Forensic audit of software repositories and technical IP for economic valuation (R&D Cost, IP Value, Acqui-hire).

This skill should be used when the user asks to "add a new skill to skillme", "add a skill to this catalog", "write an eval for this…

Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels…

Use when writing or reviewing skills to ensure no internal, confidential, or proprietary information is embedded

Advanced Content Security Policy bypass techniques.

Audit and safely repair cross-runtime Skill governance: canonical-source ownership, divergent or duplicate projections, exposure scopes…

Assess skill effectiveness from relevant agent history or scoped execution evidence.

Reviews a third-party AI agent skill — a local directory, downloaded archive, or repo URL — for safety before installing it, using…

Use as step 1 of AIS FLOWS Skill Library Cleaner when a messy AI-agent skills/source folder must be scanned without running anything…

Use as step 2 of AIS FLOWS Skill Library Cleaner to separate risky AI-agent skill/source items before cleanup, producing RISK_BLOCKLIST.md…

This skill guides the agent in managing complex, long-term penetration testing campaigns.

Quantitatively evaluates a skill when a reproducible mechanical pass/fail signal can be defined in advance: runs it on real tasks and…

Reviews a skill by first identifying whether its parts provide guidance, coordinate a workflow, or perform a task, then applies only the…

Use this skill before publishing or sharing an agent-skill bundle, generated skill fixture, release candidate, or public runbook.

Audit any SKILL.md file, AGENTS.md, system prompt, or agent-installed skill for the malicious patterns the agent-skill ecosystem fears…

Scan agent skills for security issues before adoption.

Evaluates and enhances Agent SKILL.md files by assessing self-iteration closed loops, prompt safety, and continuous learning capabilities.

Auditing and evolution of the skills ecosystem.

Security-first skill vetting for AI agents.

ISO/IEC 42001:2023 AI Management System (AIMS) specialist for compliance teams running internal audits.