codebase-onboarding

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill reconnaissance and analysis phases use standard filesystem inspection tools to identify project characteristics and do not attempt to access sensitive system files or credentials beyond standard configuration examples.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted codebase data from the repository being analyzed. 1. Ingestion points: The agent reads various codebase files including package manifests, source code, and configuration files during Phases 1-3. 2. Boundary markers: The instructions provide no specific delimiters or ignore-instructions warnings for the content read from files. 3. Capability inventory: The agent has the capability to write or modify a CLAUDE.md file and generate a Markdown onboarding guide. 4. Sanitization: No explicit sanitization or validation of the ingested content is performed before interpolation into the generated output artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 07:41 AM
Security Audit — agent-trust-hub — codebase-onboarding