funnelcockpit
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the official NPM registry, which is a vendor-provided tool for managing integrations.
- [COMMAND_EXECUTION]: Utilizes the membrane CLI to execute commands for user authentication, connection setup, and FunnelCockpit action processing as described in SKILL.md.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it retrieves external marketing data (e.g., contact info, webinar viewers) from FunnelCockpit. Ingestion points: Data entering the context through list-webinar-viewers, list-email-contacts, and list-crm-contacts in SKILL.md. Boundary markers: Absent. Capability inventory: Ability to execute shell commands via the membrane CLI in SKILL.md. Sanitization: Absent.
Audit Metadata