planning
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions do not contain any malicious patterns, obfuscation, or unauthorized data access. It operates within expected parameters for a technical planning tool.
- [PROMPT_INJECTION]: The skill analyzes external codebase files, which is an inherent surface for indirect prompt injection. This risk is assessed as safe given it is essential to the primary purpose of technical planning.
- Ingestion points: Reads codebase files and documentation (SKILL.md, Step 1.1).
- Boundary markers: No explicit delimiters are present.
- Capability inventory: The skill can write plan documents and suggest commands.
- Sanitization: No sanitization is performed on analyzed files.
Audit Metadata