The Agent Skills Directory

[SAFE]: The skill provides legitimate strategic advice for managing online reviews. No malicious command execution, data exfiltration patterns, or obfuscated content were identified within the instructions.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external customer reviews (ingestion point) via tools like LocalSEOData. While it does not define explicit boundary markers for this data (boundaries), the skill logic is limited to strategy and response generation without access to dangerous capabilities such as file system writes or subprocess execution (capability inventory). The instructions emphasize manual compliance and professional review (sanitization), making this an inherent and safe part of the intended workflow.

review-management