qa-locust-writer

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests test case specifications and performance plans from other skills or external documents to generate executable Python scripts (locustfile.py).
  • Ingestion points: Performance plans and test case specifications provided as input to the generation process (e.g., from qa-plan-creator, qa-nfr-analyst, or qa-testcase-from-docs).
  • Boundary markers: The workflow lacks explicit boundary markers or "ignore embedded instructions" directives when interpolating external content into the generated scripts.
  • Capability inventory: The skill generates Python source code and configuration files (locustfile.py, locust.conf). It does not autonomously execute the generated code.
  • Sanitization: The quality checklist mandates avoiding hardcoded secrets and using environment variables, but does not specify logic for sanitizing or escaping the content of the specifications themselves.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:38 PM
Security Audit — agent-trust-hub — qa-locust-writer