decision-mapping
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate project management and workflow orchestration. No evidence of credential harvesting, unauthorized network communication, or malicious code execution was found.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external Markdown files into the model context to maintain state across sessions. This design choice is fundamental to the skill's purpose, though it creates a potential surface for indirect prompt injection if the files contain adversarial instructions.
- Ingestion points: Reads project-relative Markdown files as specified in the 'Resume' flow in SKILL.md.
- Boundary markers: None present in the instructions.
- Capability inventory: File modification, invocation of other task-specific skills (/prototype, /grilling).
- Sanitization: No specific content sanitization or instruction filtering is performed on the loaded map files.
Audit Metadata