session-management-test-author
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions as a code-analysis and test-generation workflow that processes untrusted application metadata and source code, creating a surface for indirect prompt injection.
- Ingestion points: Application source code (src/), configurations (config/), and request captures (src/requests.js) used during the analysis.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the data being analyzed.
- Capability inventory: The workflow involves writing and executing test code in the local environment using tools like 'npm test'.
- Sanitization: No explicit sanitization or validation of the input application data is required by the workflow.
Audit Metadata