lever

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by providing instructions for the agent to ingest and process data from the Lever recruitment platform.
  • Ingestion points: The documentation in SKILL.md identifies apideck.ats.applicants.list and apideck.ats.jobs.list as methods for retrieving external data.
  • Boundary markers: The skill does not provide delimiters or specific instructions to help the agent differentiate between ingested data and system instructions.
  • Capability inventory: The skill facilitates network operations and API interactions to manage applicant and job records.
  • Sanitization: No explicit data validation or sanitization steps are defined for the information retrieved from the external API.
  • [SAFE]: The skill demonstrates safe credential management by utilizing environment variables (APIDECK_API_KEY, APIDECK_APP_ID) in code examples instead of hardcoding secrets.
  • [SAFE]: External URLs and package dependencies (@apideck/unify) are legitimate resources originating from the vendor's own infrastructure and established service domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 04:50 AM