decision-mapping

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external Markdown files (decision maps) which serves as a surface for indirect prompt injection.
  • Ingestion points: Processes content from user-provided decision map files and 'docs/agents/knowledge-vault.md' as specified in the SKILL.md file.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands embedded within the loaded Markdown content.
  • Capability inventory: The skill can invoke other functional tools including /prototype for code creation and /to-prd for project scheduling.
  • Sanitization: There is no evidence of sanitization or content validation for the decision maps before they are loaded into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 10:39 PM
Security Audit — agent-trust-hub — decision-mapping