hotjar
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified. The skill's behavior matches its described purpose of managing Hotjar data through the Membrane platform and delegating sensitive operations to the official CLI.\n- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install
@membranehq/clifrom the npm registry. This is an official tool from the skill's author (membranedev) and is a standard requirement for this integration.\n- [PROMPT_INJECTION]: The skill represents an indirect prompt injection surface as it ingests untrusted data from Hotjar (such as survey responses or feedback) which could contain malicious instructions.\n - Ingestion points: Data retrieved via
membrane action runandmembrane requestfrom Hotjar endpoints (SKILL.md).\n - Boundary markers: Not explicitly defined in the prompt instructions.\n
- Capability inventory: The agent can execute shell commands using the
membraneCLI and perform network requests via the proxy (SKILL.md).\n - Sanitization: No explicit sanitization of ingested data is performed before processing.
Audit Metadata