whatsapp-web-js
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for processing untrusted incoming data from WhatsApp messages.
- Ingestion points: The client.on('message', ...) and client.on('message_create', ...) events documented in SKILL.md and references/detailed-guide.md ingest external user input into the agent's context.
- Boundary markers: The provided code examples lack boundary markers or explicit instructions to treat message content as untrusted data.
- Capability inventory: The library enables significant automated actions, including sending messages (sendMessage), managing groups (addParticipants, promoteParticipants), and interacting with media, which could be triggered by malicious instructions embedded in messages.
- Sanitization: The documentation does not provide patterns for sanitizing or validating the content of messages before the agent acts upon them.
Audit Metadata