Tp4
- Category
- MCP Tool Poisoning
- Confidence
- 99% confidence
- Finding
The skill advertises browser-agent planning and web task assistance, but the content shown primarily directs reading local references and running an offline checker. This mismatch is dangerous because users and integrators may authorize the skill expecting one behavior while it actually performs different local/backend-style actions, undermining informed consent, review accuracy, and security assumptions about what the skill can do.
- Content
