Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 94% confidence
- Finding
- The skill declares environment-variable and network-backed capabilities in metadata, but the analyzer indicates no explicit permissions model is declared for those sensitive operations. That creates a transparency and governance gap: a user or host may invoke a seemingly simple planning skill without clearly understanding it will access API keys and make external requests. In this context, the risk is elevated because the skill routinely queries external services and depends on a secret API key, though there is no direct evidence of exfiltration or overtly malicious behavior in this file.
