meta-ads-expert
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill exhibits no malicious patterns and follows security best practices for agent-cli interactions.\n- [CREDENTIALS_UNSAFE]: The skill promotes secure credential management by instructing users to use environment variables for authentication tokens and explicitly warning against providing secrets as inline command arguments.\n- [COMMAND_EXECUTION]: All interaction with the meta-ads CLI is governed by safety flags, including --no-input for non-interactive stability and --status PAUSED to ensure all new campaigns are reviewed before going live.\n- [PROMPT_INJECTION]: The skill includes instructions for the agent to require explicit human approval before executing state-changing operations, mitigating risks from unintended autonomous actions.
Audit Metadata