Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 90% confidence
- Finding
- The skill documentation advertises execution paths that invoke Python and produce artifacts, implying shell execution and file writes, but it does not declare corresponding permissions. In an agent environment, undeclared capabilities are a security and governance problem because users and orchestration layers cannot accurately assess or constrain what the skill will do before running it.
