codebase-mapper

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill contains no executable code or scripts, and no indicators of malicious intent or obfuscation were found across the provided files.\n- [SAFE]: The instructions do not involve any network exfiltration, hardcoded credentials, or unauthorized access to sensitive system paths.\n- [PROMPT_INJECTION]: As a tool that reads and processes external codebases, the skill has an inherent indirect prompt injection surface. \n
  • Ingestion points: The skill instructions specify that the codebase-explorer agent reads the project files to generate a context brief (SKILL.md). \n
  • Boundary markers: There are no explicit instructions or delimiters provided to ensure the agent ignores or sanitizes instructions that might be embedded in the codebase being mapped. \n
  • Capability inventory: The skill involves writing generated documentation files to the .codebase-map/ directory in the project root (SKILL.md). \n
  • Sanitization: No sanitization or validation logic for the input codebase data is described in the writing or coordination guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 03:15 AM
Security Audit — agent-trust-hub — codebase-mapper