fsi-smoke-test
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from local WireMock JSON stubs to populate testing requests. This creates a surface for indirect instructions if stub files are modified, though the impact is limited to the local testing context.\n
- Ingestion points:
scripts/Invoke-FsiSmokeTest.ps1reads patient identifiers from theC:\\repos\\Fsi\\MockData\\Stubsdirectory.\n - Boundary markers: The script does not use specific delimiters to separate untrusted data from instructions.\n
- Capability inventory: The script can perform network GET and POST requests to
localhostand write results to the local temp directory.\n - Sanitization: None performed on the JSON content before processing.\n- [SAFE]: The skill interacts exclusively with local development infrastructure and does not perform any unauthorized external network operations or sensitive data access.
Audit Metadata