Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 91% confidence
- Finding
- The skill invokes a shell script (`{baseDir}/scripts/save.sh`) but does not declare permissions for shell/code execution. Undeclared execution capability is dangerous because it weakens transparency and reviewability, making it easier for a skill to perform actions the user or platform did not explicitly authorize. In this context the shell use appears functional rather than overtly malicious, but it still expands the attack surface.
