readme
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes untrusted project metadata.\n
- Ingestion points: package.json, composer.json, and other main project files (SKILL.md).\n
- Boundary markers: None found.\n
- Capability inventory: The skill instructs the agent to analyze structure and output markdown; no explicit tool definitions are present in SKILL.md.\n
- Sanitization: None specified.
Audit Metadata