Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 92% confidence
- Finding
- The skill explicitly instructs the agent to read local files, run a Python script, use network access to fetch news, and write cached dynamic token data back into configuration, yet no permissions are declared. This creates a capability/permission mismatch that can lead to over-privileged or unreviewed execution paths, making it harder for operators to understand and constrain file and network access.
