qe-cicd-pipeline-qe-orchestrator
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the orchestration of multiple agents and skills, creating a potential surface for indirect prompt injection through external data ingestion.
- Ingestion points: The skill is designed to process pipeline phase results, BDD scenarios, and requirements stored in the memory namespace.
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat external test results or requirements as untrusted content.
- Capability inventory: The skill orchestrates complex tasks across multiple agents and manages quality gate logic that can block deployments.
- Sanitization: No data validation or sanitization steps are defined for the inputs received from the CI/CD environment before they are used to influence orchestration decisions.
- [NO_CODE]: The skill consists of instructional Markdown and pseudocode templates for planning and coordination, with no executable shell scripts or binary code included.
Audit Metadata