meta-ad-policy-checker
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches live policy documentation from Meta's official transparency center (https://transparency.meta.com). These downloads target a well-known service for legitimate informational purposes.
- [COMMAND_EXECUTION]: There are no script files or shell commands included in the skill; it operates entirely through natural language instructions and web fetching.
- [DATA_EXFILTRATION]: The skill processes ad copy and advertiser context. While it makes external requests to Meta's domain, it does so to retrieve policy text rather than exfiltrate sensitive user data. Standard web fetching of public documentation is not considered a risk.
- [PROMPT_INJECTION]: The instructions are focused on adherence to advertising policies and do not contain patterns attempting to bypass agent safety filters or override system instructions.
- [CREDENTIALS_UNSAFE]: No API keys, tokens, or hardcoded secrets were detected in the skill files.
Audit Metadata