viralquery

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to https://viralquery.com/mcp to facilitate its core functionality. This endpoint is used for retrieving video data and is consistent with the stated purpose of the skill.
  • [CREDENTIALS_UNSAFE]: References to an API key format (sk_viralquery_...) in the documentation are placeholders and do not contain live secrets. The instructions correctly emphasize secure credential management by advising against placing keys in code, commits, or chat prompts.
  • [COMMAND_EXECUTION]: The skill does not perform any shell command execution or local system operations. All interactions are restricted to the four defined MCP tools (listApps, getAppVideos, requestApp, getAppRequest).
  • [DATA_EXFILTRATION]: Data transmission is limited to sending mobile app identifiers or Store URLs to the service to retrieve associated video analytics, which is the intended primary purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:45 AM
Security Audit — agent-trust-hub — viralquery