acceptance-orchestrator
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from issue trackers and acceptance criteria to drive automated coding and deployment workflows.
- Ingestion points: The workflow explicitly reads and extracts information from the
issue id,issue body, andacceptance criteria(DoD) as described inSKILL.md. - Boundary markers: Absent; there are no instructions provided to the agent to treat external content strictly as data or to ignore embedded instructions within issue descriptions.
- Capability inventory: The skill uses powerful tools including
codex-cli,claude-code, andopencodewhich allow for code implementation, git operations, and service deployments. - Sanitization: Absent; the skill does not specify any sanitization, validation, or escaping logic for the ingested issue content before it is processed by the agent.
Audit Metadata