generate-tests
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, prompt injection markers, or unauthorized data access patterns were identified in the skill instructions. The skill operates as a structured template for code analysis and test generation.- [INDIRECT_PROMPT_INJECTION]: The skill processes local source code to generate tests, which is a standard attack surface for indirect prompt injection. However, the skill lacks dangerous capabilities such as network access or shell execution, and explicitly disables model-controlled tool invocation, mitigating the risk.
- Ingestion points: Local source files or modules specified via the command-line arguments.
- Boundary markers: None explicitly defined in the instructions to separate code content from prompt context.
- Capability inventory: Limited to file reading for analysis purposes; external tool invocation is disabled.
- Sanitization: None specified for the content of the ingested code files.
Audit Metadata