firecrawl-seo-audit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external websites during the SEO audit process.
- Ingestion points: Scrapes website metadata, headings, and content from various pages (homepage, product pages, blog) into the agent context.
- Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers when the agent processes scraped data.
- Capability inventory: No dangerous capabilities such as local file writing, command execution (exec/eval), or sensitive local data access are identified in the skill instructions.
- Sanitization: No specific content sanitization, filtering, or validation of the scraped external data is mentioned.
Audit Metadata