testing
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown documentation and reference templates. It does not include any executable scripts, binaries, or active configuration files that would run code automatically.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves the agent processing and reporting on external, potentially untrusted source code and project requirements, creating a surface for indirect prompt injection. 1. Ingestion points: Untrusted data enters the agent context when it reads user-provided source code, API definitions, and testing requirements to generate tests and reports. 2. Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions for the processed data. 3. Capability inventory: The agent is instructed to generate test files (.spec.ts) and findings reports based on the ingested data. 4. Sanitization: Absent. The skill lacks instructions for sanitizing or escaping content derived from external files before its inclusion in generated output.
Audit Metadata