update-project-docs
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Potential for indirect prompt injection during documentation processing.
- Ingestion points: The skill reads 'README.md' and various documents within the 'docs/' directory to maintain context and style.
- Boundary markers: No explicit markers or delimiters are used to separate ingested content from the agent's instructions.
- Capability inventory: Performs file-system read and write operations on Markdown files.
- Sanitization: Content from ingested files is processed without validation or sanitization, potentially allowing embedded malicious instructions to influence the agent.
Audit Metadata