Automation Integration Preflight Audit report.

Warnings

• Dependency or permission surface needs review
• Permission surface may require sandboxing
• The skill does not explicitly instruct the agent to treat API response content and analyzed page content as untrusted data, leaving some risk of indirect prompt injection if the remote service or a scanned page returns malicious instructions.
• The acceptance-pack 'objective' field is sent to a third-party API; the skill warns against personal data and credentials but does not warn against confidential business information that could be present in the objective.
• There is no fallback or error-handling guidance for network failures, rate limits, malformed responses, or API unavailability.
• Low GitHub adoption signal
• Quality score needs review
• Permission surface needs review: secrets or environment access, shell or command execution
• GitHub adoption: 0 GitHub stars
• Stars/forks activity: 0 stars, 0 forks; issue activity unavailable in current metadata
• 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.