whatsapp-automation

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill includes a 'skill-report.json' file with self-referential text claiming safety to deceive analyzers. It also presents an indirect injection surface: (1) Ingestion: User inputs for 'body' and 'media_url' (SKILL.md); (2) Boundary markers: Absent; (3) Capabilities: Network-writing via WHATSAPP tools; (4) Sanitization: Absent.
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to connect to a third-party MCP server at 'https://rube.app/mcp' for its primary operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:32 PM
Security Audit — agent-trust-hub — whatsapp-automation