Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
- The skill instructs execution of multiple Python scripts that use environment variables, file I/O, and network access, yet it declares no permissions or capability boundaries. This creates a transparency and policy-enforcement gap: an agent or reviewer cannot reliably understand or restrict what the skill is allowed to access before execution, increasing the chance of over-privileged runs, unintended credential use, or data exfiltration through networked scripts.
