update-skill-learnings
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing session content and user-provided text for persistent storage.
- Ingestion points: The skill uses the
$requestargument and current session context as data sources. - Boundary markers: No explicit delimiters are used for the input data.
- Capability inventory: The skill has file modification permissions (
Edit,Write) to update repository documentation. - Sanitization: The risk is mitigated by a mandatory human-in-the-loop requirement (
AskUserQuestion) for approval of all changes, and thedisable-model-invocation: truesetting which prevents unauthorized execution.
Audit Metadata