Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the
@membranehq/clipackage via npm. This is a trusted resource provided by the skill's author ('membranedev'). - [COMMAND_EXECUTION]: Uses the
membraneCLI to execute actions (membrane action run) and make API requests (membrane request). This is the primary intended functionality of the integration. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes external messaging data.
- Ingestion points: WhatsApp messages, statuses, and business profile information (identified in SKILL.md).
- Boundary markers: Not present; the skill does not define specific delimiters to separate user data from instructions.
- Capability inventory: The skill can send multiple message types, update business profiles, and mark messages as read via the CLI (identified in SKILL.md).
- Sanitization: No explicit sanitization or validation of the incoming message content is implemented within the skill instructions.
Audit Metadata