Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 83% confidence
- Finding
- The skill explicitly instructs users to run a local shell script and use environment-backed secrets, but it does not declare permissions corresponding to its shell and file-read capabilities. This creates a transparency and policy-enforcement gap: an agent or platform may allow the skill under the assumption that it is low-privilege, while it can actually invoke shell commands and access local files or environment-derived data.
