update-claude-documentation
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository content, including code changes and existing documentation, to generate updated documentation sets.
- Ingestion points: Repository diffs, code changes, and existing documentation files (SKILL.md).
- Boundary markers: The skill does not provide specific instructions to use delimiters or ignore instructions embedded within the processed code/documentation.
- Capability inventory: The skill permits reading repository content and editing documentation files (SKILL.md).
- Sanitization: No explicit sanitization or validation of the input content is described to prevent instruction leakage from the source data into the agent's output.
- [SAFE]: No obfuscation, credential exfiltration, persistence mechanisms, or unauthorized privilege escalation patterns were identified within the skill instructions.
Audit Metadata