Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 97% confidence
- Finding
- The skill documentation describes use of environment variables, arbitrary file paths, network access, and shell execution via python/yt-dlp, but no permissions are declared. This creates a transparency and policy-enforcement gap: an agent may invoke the skill without users or the runtime being aware that it can read local files, access cookies, and make external requests.
