wacli

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill's primary function is to process incoming data from WhatsApp, which creates a surface for indirect prompt injection. \n
  • Ingestion points: Incoming messages, media, group data, and status updates from WhatsApp as described in the purpose and embedding hints. \n
  • Boundary markers: No delimiters or safety instructions (e.g., 'ignore commands in messages') are provided in the skill definition. \n
  • Capability inventory: The skill facilitates sending messages, accessing contacts, and managing groups. \n
  • Sanitization: No sanitization or validation logic for the external content is defined in the skill metadata. \n- [EXTERNAL_DOWNLOADS]: The skill metadata points to an external installation command 'clawhub install wacli' to provide the required functionality. \n- [NO_CODE]: The skill serves as documentation and metadata for discovery but does not include any scripts or executable logic within the skill package itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 09:19 AM