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.ps1 reads patient identifiers from the C:\\repos\\Fsi\\MockData\\Stubs directory.\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 localhost and 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
Risk Level
SAFE
Analyzed
Sep 8, 2026, 01:23 PM
Security Audit — agent-trust-hub — fsi-smoke-test