optimize-agent-docs
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted documentation files to create a prioritized Knowledge Manifest. Malicious instructions in source files could be promoted to the agent's core context.
- Ingestion points: Reads markdown files from .claude, .codex, .cursor, and project root (SKILL.md Phase 1).
- Boundary markers: None specified for the generated manifest content.
- Capability inventory: File read/write, find, grep, wc.
- Sanitization: None performed on ingested content.
- [COMMAND_EXECUTION]: Uses standard shell utilities (find, grep, wc) for file discovery and validation within the project directory (SKILL.md Phase 1, 5, 6).
Audit Metadata