codebase-onboarding
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It analyzes local files such as source code, package manifests, and git logs, and uses the extracted information to generate or update the project instructions in CLAUDE.md.
- Ingestion points: Reads a wide variety of repository files including package.json, go.mod, source code, and git commit history (SKILL.md).
- Boundary markers: The instructions do not define delimiters or specific constraints to prevent the agent from following malicious instructions potentially hidden within the code being analyzed.
- Capability inventory: The skill possesses the capability to write and modify the CLAUDE.md file, which serves as a persistent set of instructions for the agent within that project context.
- Sanitization: There is no explicit requirement for the agent to sanitize or validate content extracted from the codebase before it is placed into the generated documentation or configuration files.
Audit Metadata