seo-optimize
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and parses content from user-provided external URLs using DataForSEO tools.\n
- Ingestion points: External data enters the agent's context through the
on_page_content_parsingandon_page_lighthousetools as defined inSKILL.md.\n - Boundary markers: Absent. The skill instructions do not specify any delimiters or instructions to treat the parsed web content as potentially untrusted data.\n
- Capability inventory: The skill's capabilities are restricted to executing specific MCP tools for SEO metrics and reading local documentation in
docs/seo/. No system-level capabilities, subprocess execution, or write operations were identified across the instructions.\n - Sanitization: There is no evidence of sanitization or validation performed on the external content before it is processed by the model.
Audit Metadata