competitor-analysis

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to an external API service to retrieve SEO data.
  • Evidence: Connects to https://ubersuggest-mcp.neilpatelapi.com/mcp for keyword and traffic metrics, which is an official vendor resource (agents/openai.yaml).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the open web, which could contain malicious instructions designed to influence the agent's summary.
  • Ingestion points: Data enters via domain_keywords, domain_top_pages, and page_overview (SKILL.md).
  • Boundary markers: No explicit markers are defined to isolate external SEO data from the agent's instructions.
  • Capability inventory: The skill is limited to generating text-based SEO reports; it has no destructive capabilities or file-write permissions (SKILL.md).
  • Sanitization: No sanitization or filtering logic is present for retrieved web data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 08:12 AM