policy-monitor
Keep the AI policy current with practice — weekly sweep of saved AIAs, triage results, and vendor reviews to find policy drift, or direct query for a proposed new AI practice. Use when user says "policy sweep", "does our AI policy cover this", "we want to start doing X — does the policy need updating", "run the policy monitor", or on a recurring schedule.
72
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
SKILL.md describes “Sweep mode” scanning the user-configured `## Outputs` folder and extracting content from files like AIAs/triage/vendor reviews, which are outsider-authored artifacts; if those files are not authored by the operating user, their text can be ingested by the agent and used in LLM context (indirect prompt injection risk via file contents).
- Repository
- anthropics/claude-for-legal
- Commit
4a6c651
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.