The Agent Skills Directory

[SAFE]: The skill provides structured instructions for performing SEO audits and content analysis, following industry best practices.
[EXTERNAL_DOWNLOADS]: The skill involves fetching and analyzing content from external websites using tools like web_fetch and curl. This is the intended primary purpose of the skill. While this creates a surface for indirect prompt injection by ingesting untrusted data, the skill does not grant the agent capabilities that could be exploited through this vector, such as arbitrary command execution or writing to sensitive files.
[DATA_EXFILTRATION]: No patterns for exfiltrating sensitive data or unauthorized access to system credentials were found. The mention of reading .claude/product-marketing-context.md is a standard way to provide project-specific context to the agent.
[PROMPT_INJECTION]: No evidence of malicious instructions or attempts to override system safety guidelines was observed.

seo-audit