mental-model

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill directs the agent to read 'mental-model.md' and scan the repository to understand architecture. This creates an indirect prompt injection surface where codebase content could influence agent behavior.\n
  • Ingestion points: The 'mental-model.md' file and various files within the scanned repository codebase.\n
  • Boundary markers: No boundary markers or specific instructions are used to distinguish documentation text from executable agent commands.\n
  • Capability inventory: The skill utilizes the agent's ability to read and write files within the repository context.\n
  • Sanitization: The skill does not perform any sanitization or validation of the ingested documentation content before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 11:35 AM