onboard-codebase

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and interprets implementation details, comments, and project documentation from the codebase to generate its output.\n
  • Ingestion points: The skill reads directory structures, domain logic (Services, Models, Controllers), and documentation (README.md) across the repository (SKILL.md).\n
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat codebase content as untrusted data or to ignore embedded instructions (SKILL.md).\n
  • Capability inventory: The skill has the capability to read any file in the project and write updated documentation to the llmwiki/ directory and AGENT-business.md (SKILL.md).\n
  • Sanitization: No sanitization or validation of the extracted logic or documentation is performed before it is synthesized into the wiki files (SKILL.md).\n- [COMMAND_EXECUTION]: The skill requires the execution of a system command to verify the integrity of the generated documentation.\n
  • Evidence: Step 7 instructs the agent to "Run lint on generated wiki — check for contradictions." (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 09:06 AM
Security Audit — agent-trust-hub — onboard-codebase