Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 88% confidence
- Finding
- The skill documentation instructs users to execute a local shell script (`./seo-analyze.sh`) and pipe untrusted remote content into it, which indicates shell execution capability despite no declared permissions. This creates a trust and review gap: users or the platform may treat the skill as low-privilege while it actually relies on code execution and external network input, increasing the risk of command misuse, unsafe parsing, or downstream script abuse.
