whatsapp-openapi-skill

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches an OpenAPI schema from the author's GitHub repository (raw.githubusercontent.com/holon-run) to configure its operation. This is a functional requirement for the skill used to define the API interface.
  • [COMMAND_EXECUTION]: The skill executes shell commands using the uxc utility and a dynamically linked command-line wrapper to interact with the WhatsApp Cloud API. This capability is used to perform legitimate administrative and messaging tasks.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface when handling responses from the external API.
  • Ingestion points: Untrusted data enters the context via business profile and phone number metadata retrieval operations defined in SKILL.md.
  • Boundary markers: No specific delimiters or instructions are used to separate API-returned data from agent instructions.
  • Capability inventory: The skill can execute shell commands through the uxc tool (SKILL.md) and perform outbound network actions via message sending (references/usage-patterns.md).
  • Sanitization: The skill does not perform sanitization or validation of the data retrieved from the WhatsApp API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 03:14 AM