evolution-api

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill teaches the agent to process data from external WhatsApp conversations via the Evolution API, creating an ingestion point for untrusted data. \n
  • Ingestion points: The MESSAGES_UPSERT webhook event described in SKILL.md and references/events.md allows external message content to enter the agent context. \n
  • Boundary markers: The instructions lack specific delimiters or warnings to ignore potentially malicious instructions embedded in incoming messages. \n
  • Capability inventory: The skill provides extensive capabilities for sending messages, managing groups, and configuring AI integrations through the API. \n
  • Sanitization: No sanitization or validation logic is defined in the instructions for handling message content. \n- [NO_CODE]: The skill consists entirely of markdown documentation and reference files, with no associated scripts or executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 11:03 PM
Security Audit — agent-trust-hub — evolution-api