Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 91% confidence
- Finding
- The skill instructs the agent to execute shell commands (`bash scripts/sync-feishu.sh`, `bash scripts/create-github-issue.sh`, `git ...`) but does not declare permissions or otherwise signal that command execution is required. This creates a trust and review gap: a user may invoke the skill expecting document editing, while the agent is guided to run local scripts and network-capable tooling that can access credentials, modify files, and transmit data externally.
