linkfox-google-aimodel-search

Pass

Audited by Gen Agent Trust Hub on May 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from the internet via a dedicated API endpoint (tool-gateway.linkfox.com). This is a documented functionality for retrieving AI-generated search summaries and web citations.
  • [DATA_EXFILTRATION]: User queries, follow-up prompts, and telemetry are transmitted to the vendor's API and feedback endpoints (linkfox-ai.com subdomains). These actions are inherent to the skill's service model and relate directly to the author's infrastructure.
  • [PROMPT_INJECTION]: The skill ingests and summarizes third-party content from Google search results, creating a surface for potential indirect prompt injection. However, this is inherent to its primary research purpose.
  • Ingestion points: Fetches unstructured text via the stdout field in API responses from Google AI Overview.
  • Boundary markers: None defined for external content.
  • Capability inventory: Summarizes and presents external Markdown to the user.
  • Sanitization: None specified in instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 30, 2026, 12:05 AM