skills/sanjay3290/ai-skills/whatsapp/Gen Agent Trust Hub

whatsapp

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/wa.py script utilizes os.execv to perform process replacement, ensuring it runs under a specific Python interpreter within its managed virtual environment. It also executes the local scripts/_bootstrap.sh file using subprocess.run to handle initial environment setup.- [EXTERNAL_DOWNLOADS]: The scripts/_bootstrap.sh script installs the pywhats and qrcode libraries from the official Python Package Index (PyPI).- [CREDENTIALS_UNSAFE]: To maintain its connection as a companion device, the skill stores WhatsApp authentication sessions and Signal protocol databases in the user's ~/.pywhats directory. This is intended functionality for the skill's messaging capabilities.- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection through the listen subcommand which processes incoming WhatsApp messages.
  • Ingestion points: External messages received via scripts/wa.py listen in scripts/wa.py.
  • Boundary markers: Not present in the JSON-formatted event stream.
  • Capability inventory: Messaging commands in scripts/wa.py including send-text, send-image, and group-send.
  • Sanitization: Not present.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 06:10 PM
Security Audit — agent-trust-hub — whatsapp