Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 94% confidence
- Finding
- The skill instructs the agent to perform shell execution plus file reads and writes, but it declares no permissions or trust boundaries. This is dangerous because users and the platform cannot clearly see that the skill can invoke local commands, read local files such as transcripts/templates, and write outputs into the filesystem, which increases the chance of unintended or unauthorized local access.
