Security audit
Security checks for vulnerabilities and agentic risk
This is a transparent Markdown-only research skill that gathers public AI-tool information and writes user-requested playbooks, catalogs, and a run log.
Before installing, be comfortable with the skill using web search and writing or updating Markdown files in the chosen output directory. Treat generated third-party skill install commands as recommendations to review and vet before running, especially for tools that can access the shell or private accounts.
Referenced artifact was not completely inspected
All five honor the [agentskills.io](https://agentskills.io) open `SKILL.md` standard, so skills from one ecosystem often work in another — this is called out in
Referenced artifact was not completely inspected
All five honor the [agentskills.io](https://agentskills.io) open `SKILL.md` standard, so skills from one ecosystem often work in another — this is called out in
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
# Project-local
mkdir -p .cursor/skills
cp -r ai-tool-research-skill .cursor/skills/ai-tool-research
# OR personal (shared across all your Cursor projects)
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
mkdir -p ~/.claude/skills
cp -r ai-tool-research-skill ~/.claude/skills/ai-tool-research
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
mkdir -p ~/.codex/skills
cp -r ai-tool-research-skill ~/.codex/skills/ai-tool-research
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
mkdir -p ~/.gemini/skills
cp -r ai-tool-research-skill ~/.gemini/skills/ai-tool-research
The tone rule mandates a fixed linguistic style ('Third person. Never "you can…" or "we recommend…"') for all generated playbooks. Under the policy, language/locale constraints should not be forced without opt-in or clear justification, and this template does not provide such flexibility.
No suspicious patterns detected.