Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 94% confidence
- Finding
- The skill explicitly instructs the agent to run shell commands such as `npm install` and multiple scripts under `scripts/`, yet the metadata does not declare any corresponding permissions or execution capabilities. This creates a trust and review gap: operators may approve or invoke the skill without realizing it can execute local commands, install dependencies, and process untrusted inputs through the shell.
