Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
- The skill documentation indicates capabilities to read environment variables and perform network access, yet it declares no explicit permissions. This creates a transparency and governance gap: users or orchestrators may invoke a skill that can access a bearer token and send data to an external API without an upfront permission model. In an agent setting, undeclared env and network access materially increase the risk of unintended token use or data exfiltration.
