meta-ad-policy-checker
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely within the AI agent's instructional context, using standard search and web fetching capabilities to retrieve public policy documents from
transparency.meta.com. All identified processes (intake, policy resolution, reasoning, and output) follow standard safety practices for content auditing. - [REMOTE_CODE_EXECUTION]: No remote code execution patterns or package installations were detected. The skill uses web retrieval for documentation purposes only.
- [DATA_EXFILTRATION]: The skill does not access sensitive system files or credentials. Its operations are limited to the ad copy provided by the user and public information from Meta.
- [PROMPT_INJECTION]: No prompt injection or behavior override patterns were found. The instructions are clearly scoped to ad policy auditing.
- [COMMAND_EXECUTION]: The skill does not utilize shell commands or subprocess calls. The integration hooks mentioned are logical workflow connections for the agent, not executable system commands.
Audit Metadata