document
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from the repository codebase to generate documentation, which presents a surface for indirect prompt injection.
- Ingestion points: Reads all repository files, including source code, configurations, and scripts, within the
<WORKSPACE_ROOT>directory. - Boundary markers: The instructions do not define specific delimiters or instructions for the subagent to disregard malicious content embedded within the analyzed files.
- Capability inventory: The skill utilizes file system reading and subagent spawning to produce markdown text; it does not perform automated shell execution or network requests.
- Sanitization: No specific sanitization or filtering logic is defined for the content extracted from the repository before it is processed by the documentation subagent.
Audit Metadata