whatsapp-openapi-skill
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a curated OpenAPI schema from the author's repository on GitHub to configure the command-line interface for WhatsApp operations.
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands using the
uxcutility to manage authentication, perform asset discovery, and send messages. - [INDIRECT_PROMPT_INJECTION]: Ingestion points: The skill ingests data from the WhatsApp Business Platform via operations like
get:/{phone_number_id}/whatsapp_business_profile. Boundary markers: The instructions do not specify explicit delimiters or boundary markers for the data returned from the API. Capability inventory: The skill includes powerful write capabilities, such as sending outbound messages and updating business profiles. Sanitization: The skill implements a guardrail that requires explicit user confirmation before executing high-risk write operations to mitigate risks from unexpected input.
Audit Metadata