Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 89% confidence
- Finding
- The skill instructs the agent to execute multiple shell scripts (`bootstrap.sh`, `start.sh`, `healthcheck.sh`, `smoke-test.sh`) but does not declare any permissions for shell/code execution. This creates a transparency and policy-enforcement gap: an agent or platform may run privileged local commands without users having explicit visibility or approval boundaries, increasing the risk of unintended system changes or abuse if the referenced scripts are modified or malicious.
