qa-orchestrator

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill coordinates pipelines that ingest untrusted external data (URLs, Figma designs, and API contracts) to generate testing documentation and code.
  • Ingestion points: Processes external assets like app URLs, design files, and Swagger/OpenAPI specifications as described in the Full E2E and UI-first chains.
  • Boundary markers: The orchestration logic does not specify explicit delimiters or "ignore" instructions for the sub-skills it invokes, relying on the sub-skills' internal logic.
  • Capability inventory: The skill triggers a sequence of sub-skills that perform file system reads, code generation for frameworks like Playwright and Supertest, and project documentation updates.
  • Sanitization: No explicit sanitization or validation of the external content is performed at the orchestration layer, delegating this to individual specialized skills in the handoff chain.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:38 PM
Security Audit — agent-trust-hub — qa-orchestrator