plan
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from local project files (PROJECT.md, AGENTS.md) and design documents, which could theoretically contain malicious instructions. 1. Ingestion points: Reads project documentation and design specifications. 2. Boundary markers: The skill instructions do not specify delimiters to separate untrusted file content from system instructions. 3. Capability inventory: The skill is restricted to text generation only; it is explicitly prohibited from writing code, building, or testing. 4. Sanitization: No sanitization or filtering of external content is defined.
- [SAFE]: No malicious patterns, obfuscation, persistence mechanisms, or unauthorized privilege escalations were detected. The skill's functionality is strictly limited to planning and logical decomposition.
Audit Metadata