linkedin

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill employs standard browser automation tools to interact with LinkedIn, which is necessary for its declared purpose of profile auditing. The process includes a verification step to ensure the correct page is being analyzed.\n- [SAFE]: There are no indicators of prompt injection, role-play bypasses, or instructions to ignore safety filters. The skill maintains a professional instructional tone.\n- [SAFE]: No credentials, sensitive local files, or unauthorized network operations were detected. The skill does not attempt to send data to external third-party domains.\n- [SAFE]: While the skill ingests content from external LinkedIn profiles, which is a potential surface for indirect prompt injection, it does so to fill predefined templates and perform metrics-based analysis, minimizing the risk of executing unintended commands.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 02:52 PM
Security Audit — agent-trust-hub — linkedin