meta-ads
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: A comprehensive analysis across all threat vectors revealed no malicious activity or security vulnerabilities.
- [COMMAND_EXECUTION]: The skill provides utility scripts for campaign management and permission verification. These scripts are strictly scoped to the user's provided configuration and interact only with official Meta Marketing API endpoints.
- [CREDENTIALS_UNSAFE]: Secret management follows industry best practices by utilizing environment variables (
META_ADS_TOKEN) instead of hardcoding sensitive data. The documentation includes clear instructions on how to handle and rotate tokens securely. - [DATA_EXFILTRATION]: Network activity is confined to legitimate interactions with well-known service domains (
facebook.com). The skill does not attempt to exfiltrate local files or sensitive user information to unauthorized third parties. - [INDIRECT_PROMPT_INJECTION]: The skill defines a clear boundary for external data through a structured configuration file. It includes internal safeguards, such as copy validation and budget assertions, to prevent malicious or accidental misconfiguration from affecting the agent's behavior.
Audit Metadata