ucs-api
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes API specification files from docs/specs/API/ which could contain malicious instructions if they originate from an untrusted source.
- Ingestion points: The agent reads and processes all YAML files found in the docs/specs/API/ directory (SKILL.md).
- Boundary markers: The instructions do not define clear boundaries or 'ignore' instructions for the content being processed by subagents, increasing the risk of the agent following instructions contained within the data.
- Capability inventory: The skill has the ability to write files to the local file system (docs/specs/API-UCS/) and delete directories (docs/specs/API-UCS-review/) (SKILL.md).
- Sanitization: There is no evidence of content sanitization or validation of the input YAML files before they are utilized in prompts.
Audit Metadata