seo-mcp-tools-expert

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core functionality involves fetching and analyzing untrusted content from external URLs.
  • Ingestion points: Content is ingested from user-provided URLs using tools like analyze_page and analyze_headings, as described in SKILL.md and the AUDIT_WORKFLOW_GUIDE.md.
  • Boundary markers: The skill does not provide the agent with instructions to use delimiters or boundary markers to distinguish between its own instructions and content fetched from external sites.
  • Capability inventory: The agent is equipped with various tools (e.g., analyze_page, analyze_internal_links, check_core_web_vitals) that perform network requests and generate detailed reports based on the findings.
  • Sanitization: There are no explicit instructions or mechanisms defined for the agent to sanitize or ignore potential instructions embedded within the HTML, meta tags, or other components of the analyzed web pages.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 04:05 PM