The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill instructions or supporting files.
[DATA_EXPOSURE]: The skill instructs the agent to read local context files, such as .agents/product-marketing.md, to gain business context before starting an audit. This is an appropriate use of project-specific information and no mechanisms for exfiltrating this data were found.
[EXTERNAL_DOWNLOADS]: The skill references several well-known and trusted search engine optimization tools and documentation sources, including Google Search Central, Bing Webmaster Tools, and established industry blogs (e.g., Search Engine Journal, Semrush, Yoast). These are documented for auditing purposes and are considered safe.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves fetching and analyzing external website content via web_fetch or curl. While this represents an ingestion point for untrusted data, the skill's logic is focused on generating an audit report rather than executing commands or modifying system state based on the fetched content, minimizing the risk of exploitation.

seo-audit