breakdown-epic-pm
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were found in the skill. The logic is focused on document generation and follows standard instructional patterns.
- [PROMPT_INJECTION]: Analyzed the skill for indirect prompt injection risks. The skill ingests user input and writes to files, which is its core intended functionality. 1. Ingestion points: The 'Epic Idea' field in the context template. 2. Boundary markers: Input is placed within a structured context template. 3. Capability inventory: Writing files to the /docs/ways-of-work/plan/ directory. 4. Sanitization: No explicit sanitization or validation is defined in the prompt, relying on the agent's internal safety controls.
Audit Metadata