codebase-onboarding

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted repository content, creating a vulnerability surface where malicious instructions in codebase documentation could attempt to influence agent behavior.
  • Ingestion points: Repository source files, build configurations, and documentation (e.g., README.md) scanned during the onboarding workflow in SKILL.md and rules/ files.
  • Boundary markers: The skill produces structured output with specific section headers as defined in references/artifact-schema.md, but lacks explicit boundary markers or instructions for the agent to ignore natural language commands found within the input files being scanned.
  • Capability inventory: The skill primarily uses filesystem read operations to orient the agent; it also includes internal validation scripts (tests/run-validation.py) that use subprocess to execute the local validator.
  • Sanitization: No explicit sanitization or filtering of the content extracted from repository files is specified before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 03:18 PM