ucs-ws
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs local file operations (read/write) within the docs/ and templates/ directories to facilitate documentation generation. It does not perform network operations, execute remote code, or require elevated privileges.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project files (AsyncAPI YAML, business flows, and database specifications) which are then used by a subagent to generate documentation. While this creates a theoretical surface for indirect prompt injection, the risk is minimal as it processes local project files and the output is restricted to markdown documentation within the same project. 1. Ingestion points: docs/specs/ws/*.yaml, docs/product/business-flow.md, docs/specs/data/. 2. Boundary markers: Not explicitly defined in the subagent prompt. 3. Capability inventory: Reads local files and writes generated content to docs/specs/ws-UCS/. 4. Sanitization: None identified; the agent relies on standard processing of input files.
Audit Metadata