seo-coach
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define a benign persona for assisting users with SEO tasks. It provides educational guidance on using specific tools like Google Search Console and OpenSEO MCP data, as well as general web research techniques.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a standard attack surface for indirect prompt injection because it is designed to process data from external, untrusted sources like web search results and page scraping.
- Ingestion points: Data retrieved via web search and browser-based page scraping (SKILL.md).
- Boundary markers: None explicitly defined in the prompt instructions to isolate external data.
- Capability inventory: Execution of MCP tools, web searching, and file system operations (SKILL.md).
- Sanitization: No specific sanitization or filtering logic is prescribed for the external content before it is processed by the agent.
Audit Metadata