Lever Automation
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to add an external MCP server configuration from
https://rube.app/mcp, which is the infrastructure used by the vendor to provide tool access. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from Lever ATS, such as candidate profiles and job postings, which can contain untrusted content designed to influence the agent's behavior.
- Ingestion points: Data is ingested through tools like
LEVER_LIST_POSTINGS,LEVER_LIST_OPPORTUNITIES, andLEVER_GET_OPPORTUNITYas described in SKILL.md. - Boundary markers: There are no specified delimiters or instructions for the agent to ignore or isolate embedded instructions within the retrieved data.
- Capability inventory: The skill includes write capabilities such as
LEVER_UPDATE_REQUISITIONandLEVER_DELETE_REQUISITION(SKILL.md). - Sanitization: No sanitization or filtering of the retrieved recruiting data is described in the skill's instructions.
Audit Metadata