sales-lemlist

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to process external data from the Lemlist platform.
  • Ingestion points: Data retrieved from the Lemlist People Database, Lead management, and Unified Inbox as documented in references/lemlist-api-reference.md.
  • Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious commands embedded within retrieved lead or message data.
  • Capability inventory: The skill provides instructions and references for automated actions including sending emails and LinkedIn messages via API endpoints (POST /inbox/send/email, POST /inbox/send/linkedin).
  • Sanitization: No sanitization or content validation procedures are described for data fetched through the Lemlist API.
  • [SAFE]: All referenced domains and endpoints (lemlist.com) belong to a well-known technology service. No unauthorized access or exfiltration patterns were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 09:42 AM