Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 90% confidence
- Finding
- The skill explicitly instructs the agent to create, read, and write local files such as config.json, history.json, temporary search-result files, and output digests, yet no permissions are declared. This creates a mismatch between the skill's documented behavior and its permission model, which can lead to unauthorized filesystem access or unsafe execution assumptions by the host environment.
