acceptance-orchestrator
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (issue bodies and acceptance criteria) which serves as an attack surface for indirect prompt injection. A malicious actor could embed instructions within a code issue to attempt to subvert the agent's logic or influence the output contract.
- Ingestion points: The skill reads issue IDs and issue bodies to extract goals and Definition of Done (DoD) markers as described in the 'Intake' section of
SKILL.md. - Boundary markers: There are no explicit instructions to use delimiters or ignore embedded natural language instructions within the ingested issue content.
- Capability inventory: The skill manages full implementation cycles, including repository modifications and environment deployments (via referenced sub-skills like
closed-loop-delivery). - Sanitization: The skill lacks explicit sanitization or validation logic for the input data, though it mitigates the risk through 'Human Gates' for destructive or high-impact operations.
Audit Metadata