sa
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process and analyze external data sources, specifically Product Requirement Documents (PRDs) and existing project test files.
- Ingestion points:
SKILL.md(Step 3: Validate Tests) directs the agent to search and read project test files;references/system_design_doc.mdrelies on content from external PRD specifications. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within user-provided documentation.
- Capability inventory: The skill performs file system reads (to find and analyze tests) and writes documentation (the System Design Document). It does not execute the data as code or perform network operations.
- Sanitization: No explicit sanitization of PRD or codebase content is mentioned.
Audit Metadata