decision-mapping

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes an external Markdown file (the 'decision map') and loads its entire content into the agent's context during the 'Resume' phase. This creates a surface for indirect prompt injection where malicious instructions embedded in a project's map file could influence the agent's behavior.
  • Ingestion points: The skill loads the whole map file as context in the Resume workflow described in SKILL.md.
  • Boundary markers: Absent. The instructions do not specify any delimiters or warnings to prevent the agent from following instructions found within the map file.
  • Capability inventory: The skill can invoke other agent capabilities such as /prototype (code generation) and performs file system writes to update the map.
  • Sanitization: Absent. The skill does not describe any validation or filtering of the content loaded from the markdown file.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 02:22 PM
Security Audit — agent-trust-hub — decision-mapping