lever
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli tool from the npm registry which is the primary interface for the service.
- [COMMAND_EXECUTION]: Instructions rely on the membrane CLI to perform shell-based operations for authentication and API interaction.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Lever ATS such as candidate notes and job postings which creates an attack surface for indirect prompt injection. Ingestion points: External Lever data (Leads, Notes, Postings) as specified in SKILL.md. Boundary markers: No specific delimiters or instructions to ignore embedded content are used. Capability inventory: The skill possesses network capabilities and write access to the Lever API via the CLI. Sanitization: No sanitization or validation of the retrieved content is mentioned.
Audit Metadata