map-codebase

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface\n
  • Ingestion points: The skill performs a wide-scale scan and read of the codebase's source files in Step 1 to build a file manifest for analysis.\n
  • Boundary markers: The skill does not employ delimiters or specific instructions to isolate the content of the read files from the agent's operational instructions.\n
  • Capability inventory: The skill is capable of writing multiple files to the local file system (.turbo/codebase-map.md and .turbo/codebase-map.html) based on its findings.\n
  • Sanitization: There is no evidence of sanitization or filtering of the content read from source files before it is processed and summarized by the inspection agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 05:23 PM
Security Audit — agent-trust-hub — map-codebase