viralquery

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were detected in the skill instructions or configuration.
  • [CREDENTIALS_UNSAFE]: The skill adheres to best practices for secret management by instructing the agent to read the API key from a configured environment variable or secret ($VIRALQUERY_API_KEY) and explicitly forbidding its inclusion in chat outputs or source files.
  • [EXTERNAL_DOWNLOADS]: Network operations are restricted to the official ViralQuery API domain (api.viralquery.com) for its intended purpose of fetching app and video data.
  • [COMMAND_EXECUTION]: No arbitrary command execution or shell interactions were found; the skill relies solely on structured HTTP requests.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied app names and App Store links, it instructs the agent to perform extraction of numeric IDs and use JSON formatting, which provides a layer of data sanitization against injection attempts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 02:41 AM
Security Audit — agent-trust-hub — viralquery