acceptance-orchestrator
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill logic is entirely instructional and focused on orchestration without any executable code or dangerous command patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from issue bodies and acceptance criteria which is a known surface for indirect prompt injection. 1. Ingestion points: Issue body and DoD criteria extracted from the task intake. 2. Boundary markers: No explicit delimiters or boundary warnings are present in the orchestrator logic. 3. Capability inventory: Deployment to dev environments, implementation of code, and git operations through sub-skills. 4. Sanitization: No sanitization of the input text is described in the workflow.
Audit Metadata