contract-test-writer
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and provides best practices for setting up Pact contract tests.
- [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found in the documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to analyze external inputs such as consumer code and provider documentation to generate test cases. While this constitutes an ingestion point, the risk is minimal as the skill defines a specific, limited scope for generated output and involves no automated execution of the ingested data.
- Ingestion points: Consumer source code and provider API documentation (Step 1.2).
- Boundary markers: The instructions explicitly define the scope to only include consumed fields and matchers.
- Capability inventory: No scripts or tool execution capabilities are defined within this skill.
- Sanitization: Not explicitly defined within the skill itself, as the output is intended for developer implementation.
Audit Metadata