linkedin-navigation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes untrusted external data from LinkedIn which creates a surface for indirect prompt injection.
  • Ingestion points: Uses mcp__claude-in-chrome__read_page and mcp__claude-in-chrome__take_snapshot to read data from the LinkedIn feed, messaging, and notifications.
  • Boundary markers: Absent. The instructions do not define delimiters to separate the retrieved page content from the agent's instructions.
  • Capability inventory: Possesses browser automation tools including mcp__claude-in-chrome__navigate, mcp__claude-in-chrome__click, and mcp__claude-in-chrome__form_input.
  • Sanitization: Absent. There is no evidence of filtering or sanitizing the retrieved content.
  • [Safe Best Practices] (SAFE): The skill explicitly enforces a policy of not handling passwords, instructing the user to log in manually instead. This prevents credential harvesting by the skill itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:16 PM