seo-master

Warn

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to suggest installing an extension from an untrusted GitHub repository (github:mindverse/skillhub) if the user needs advanced SEO data or competitive analysis.
  • [PROMPT_INJECTION]: The skill processes untrusted website data and URLs during analysis without boundary markers or instructions to ignore embedded commands, creating a risk of indirect prompt injection. Ingestion points: User-provided URLs and site descriptions. Boundary markers: None identified. Capability inventory: Generation of meta tags, title tags, and JSON-LD structured data scripts. Sanitization: None identified.
  • [NO_CODE]: The skill contains only instructions and lacks any executable code or scripts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 1, 2026, 03:44 PM