holistic-testing-pact

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data such as requirements, user stories, and API designs to generate testing strategies. This constitutes an indirect prompt injection surface.
  • Ingestion points: Data enters the agent context through the qe-requirements-validator and qe-test-generator agents during refinement and planning phases (referenced in SKILL.md).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions within processed data are defined in the provided snippets.
  • Capability inventory: The skill utilizes FleetManager.coordinate to orchestrate multiple agents and Task calls to perform analysis and risk planning.
  • Sanitization: There is no evidence of sanitization or validation of the input requirements before they are processed by the agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 08:42 AM