helpcrunch
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the Membrane CLI tool (@membranehq/cli) globally from the npm registry to enable interaction with the service.\n- [COMMAND_EXECUTION]: It executes shell commands via the membrane CLI to authenticate, manage connections, and run integration actions.\n- [DATA_EXFILTRATION]: It communicates with HelpCrunch's external APIs through the Membrane platform to sync and manage customer data.\n- [PROMPT_INJECTION]: The skill processes untrusted content from HelpCrunch (e.g., chat messages and customer metadata), creating a potential surface for indirect prompt injection.\n
- Ingestion points: External data fetched via HelpCrunch API actions such as get-chat-messages and list-customers.\n
- Boundary markers: No specific delimiters or security instructions for processing untrusted content are provided.\n
- Capability inventory: Shell command execution via CLI and the ability to run or create integration actions.\n
- Sanitization: No explicit content sanitization or validation is mentioned in the documentation.
Audit Metadata