dor-gate
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill.
- [DATA_EXFILTRATION]: The skill is designed to read local project artifacts from the team-artifacts/pbis/ directory and configuration protocols from .claude/skills/shared/. There are no network-capable tools, URLs, or commands that would enable data exfiltration or external communication.
- [PROMPT_INJECTION]: While the instructions use emphatic language like "MANDATORY IMPORTANT MUST", these are used to enforce a specific quality-control workflow and do not represent attempts to bypass AI safety guardrails or override system instructions.
- [COMMAND_EXECUTION]: The skill uses safe, standard agent tools like TaskCreate and AskUserQuestion for process management and does not execute arbitrary shell commands or external scripts.
Audit Metadata