update-lib-docs
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill is vulnerable to indirect prompt injection because it ingests untrusted data from web searches and saves it to local documentation.
- Ingestion points: Web search results for latest library information, breaking changes, and security updates (Step 2).
- Boundary markers: Absent. The skill does not instruct the agent to distinguish between documentation data and potential instructions embedded in the search results.
- Capability inventory: Execution of the
lscommand and local file-write operations to the.claude/docs/libraries/directory. - Sanitization: Absent. There is no validation or filtering of the content retrieved from external websites before it is used to update internal files.
Audit Metadata