onboard-codebase
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an unmapped codebase, including README files and source code comments, which could contain malicious instructions designed to influence the agent's output.
- Ingestion points: The skill reads all project files during the Infrastructure Audit and Deep Code Analysis steps in SKILL.md.
- Boundary markers: There are no explicit instructions to ignore embedded prompts within the source material.
- Capability inventory: The skill has the ability to write to multiple local markdown files within the llmwiki directory.
- Sanitization: No sanitization or validation of the ingested code content is specified before it is synthesized into the wiki.
Audit Metadata