ad-creative

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns such as prompt injection, obfuscation, or persistence mechanisms were detected in the skill instructions or metadata.
  • [COMMAND_EXECUTION]: The skill utilizes the 'bash' and 'git' tools to perform routine tasks such as reading logs, running tests, and managing project history, which is consistent with its stated purpose in a development or marketing environment.
  • [EXTERNAL_DOWNLOADS]: The instructions describe pulling existing ad copy and performance data via Google Ads API or other MCP tools. These references target well-known services and are used exclusively for the skill's primary function of creative optimization.
  • [DATA_EXFILTRATION]: No unauthorized data harvesting patterns were identified. The data access described is limited to performance metrics necessary for generating ad variations as per the user's requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 02:51 PM
Security Audit — agent-trust-hub — ad-creative