api-contract-testing
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute a Python script located at
../api-design-rest/scripts/validate_api_contract.pyto validate API manifests. This is a standard workflow within a multi-component repository and involves a local relative path. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is designed to ingest and process external provider specifications and consumer expectations. Ingestion points: API specifications and consumer integration case files (SKILL.md). Boundary markers: No specific delimiters or safety instructions are defined for processing these inputs. Capability inventory: The skill executes Python-based validation logic (SKILL.md). Sanitization: No input sanitization or validation steps are outlined.
Audit Metadata