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, and acceptance criteria (DoD) as described in SKILL.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, and opencode which 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
Risk Level
SAFE
Analyzed
Aug 7, 2026, 09:22 PM
Security Audit — agent-trust-hub — acceptance-orchestrator