plan-privacy-compliance
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is strictly instructional and does not contain any executable scripts, shell commands, or binary files. It functions as a roadmap for an AI agent to perform a manual audit.
- [SAFE]: The instructions explicitly state that the skill is for planning and auditing only. It warns against executing SDK gates or deletion jobs until the plan is approved, which enforces a safe operational boundary.
- [SAFE]: No prompt injection, data exfiltration, or obfuscation techniques were found. References to 'exfiltration' within the text correctly describe the behavior of third-party SDKs that the agent is tasked with auditing, rather than implementing exfiltration itself.
- [SAFE]: The skill lacks network capabilities and does not request access to sensitive local files or credentials.
Audit Metadata