The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or obfuscated instructions were found. The skill defines a legitimate auditing workflow.
[COMMAND_EXECUTION]: The usage of bash and git is described for standard development tasks such as reading logs and committing project changes, consistent with an agent operating in a developer environment.
[DATA_EXFILTRATION]: While the skill interacts with advertising APIs, this is necessary for its core function of auditing campaign data. No instructions were found to access or exfiltrate sensitive local files like credentials or SSH keys.

paid-media-auditor