Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 94% confidence
- Finding
- The skill invokes shell commands (`codexbar`, `python`) and reads local files/stdin, but it does not declare any tool scope such as `permissions` or `allowed-tools`. That creates an authorization gap where an agent may execute shell/file operations without an explicit, reviewable boundary, increasing the chance of unintended command execution or access to local cost logs and arbitrary input files.
