Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 83% confidence
- Finding
- The skill advertises and invokes file read/write and shell-based script execution, but does not declare corresponding permissions or trust boundaries. This creates a transparency and consent problem: users or hosting platforms may authorize the skill without understanding that it can modify files or execute subprocesses, increasing the chance of unsafe use or privilege misuse.
