chengfeng-report-bug Audit report.

Warnings

• Dependency or permission surface needs review
• Permission surface may require sandboxing
• openai.yaml sets allow_implicit_invocation: true, which may cause the skill to be triggered in ambiguous contexts even though the description tries to restrict it. Explicit invocation would better match the confirmation-heavy workflow.
• The review only had access to an excerpt of report-bug.cjs; the full script should be audited to confirm that all user-controlled fields are properly escaped and that the confirmation receipt is single-use and bound to the exact draft content.
• Quality score needs review
• Permission surface needs review: secrets or environment access, shell or command execution
• Dependency/runtime risk: command execution surface, credential or environment access
• Permission surface: secrets or environment access, shell or command execution

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.