idea-autopsy

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a project file named REJECTION.md to identify previous business idea failures.
  • Ingestion points: The agent reads the contents of REJECTION.md in the current project directory (Step 1).
  • Boundary markers: No explicit boundary markers or ignore instructions are used when interpolating the file content into the agent context.
  • Capability inventory: The skill is limited to reading and writing (appending) to the REJECTION.md file. It does not possess network, shell command, or arbitrary code execution capabilities.
  • Sanitization: No specific sanitization or filtering of the markdown content is performed before processing the idea kill-list.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 08:08 AM
Security Audit — agent-trust-hub — idea-autopsy