codebase-exploration

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it retrieves and analyzes content from the local codebase that could contain adversarial instructions. \n
  • Ingestion points: File contents and directory structures are read using rg, fd, and ast-grep as described in SKILL.md and REFERENCE.md. \n
  • Boundary markers: Absent. The instructions do not define delimiters or specific warnings for the agent to distinguish between its instructions and the data being analyzed. \n
  • Capability inventory: The skill enables filesystem search operations and reads file content. \n
  • Sanitization: Absent. The skill does not perform validation or escaping on data retrieved from the codebase before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 08:31 AM
Security Audit — agent-trust-hub — codebase-exploration