Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
- Without declared permissions the skill's intent is opaque and cannot be validated.
Security checks across malware telemetry and agentic risk
This is a disclosed browser-automation skill with normal web automation privacy risks, but no evidence of hidden exfiltration, persistence, or deceptive behavior.
Install this only if you want your agent to control a browser. Use allowed-host settings for trusted domains, verify form submissions and file uploads before running them, avoid entering secrets on untrusted sites, and disable trace/video capture unless needed because those outputs may contain sensitive page data.
64/64 vendors flagged this skill as clean.