cicd-pipeline-qe-orchestrator

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as an orchestration layer that consumes data from various CI/CD pipeline phases and external agents, creating a surface for indirect prompt injection.
  • Ingestion points: The skill retrieves and processes data from the aqe/pipeline/ memory namespace, including phase-results/*, security/findings, and test-plan/generated, as specified in the coordination hints of SKILL.md.
  • Boundary markers: The provided instructions do not define explicit delimiters or 'ignore' directives to isolate the orchestrator's logic from instructions that might be embedded within the ingested test reports, security findings, or external service responses.
  • Capability inventory: The orchestrator possesses the authority to coordinate 19 specialized agents with significant capabilities, including code generation (qe-test-generator), test execution (qe-test-executor), and deployment readiness assessment (qe-deployment-readiness), as described in SKILL.md and README.md.
  • Sanitization: No sanitization, validation, or filtering mechanisms are described for the data ingested from the shared memory namespace before it is used to influence the orchestration logic and subsequent agent task assignments.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:15 PM
Security Audit — agent-trust-hub — cicd-pipeline-qe-orchestrator