NYC

automate-whatsapp

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection. It enables the retrieval of untrusted user data from external messaging channels (WhatsApp) via scripts like get-execution.js. This data enters the agent's context and could contain malicious instructions designed to manipulate the agent.\n
  • Ingestion points: scripts/get-execution.js, scripts/get-context-value.js, and scripts/list-executions.js all return data containing external user input.\n
  • Boundary markers: No explicit delimiters or instructions for the agent to treat retrieved data as untrusted are found in the documentation or scripts.\n
  • Capability inventory: The skill possesses high-privilege capabilities on the Kapso platform, including the ability to modify automation logic and deploy executable code.\n
  • Sanitization: The skill does not perform any sanitization or validation of the data retrieved from the remote API, passing it directly to the agent in JSON format.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:50 PM