Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 89% confidence
- Finding
- The skill advertises capabilities to read environment variables, local session files, invoke a binary, and make network-backed API requests, but it does not declare any permissions or trust boundaries. That creates a transparency and policy-enforcement gap: an agent may execute sensitive operations such as reading `OPENROUTER_API_KEY` or scanning `~/.openclaw/...` without explicit user-visible authorization, which is especially risky in a skill that accesses billing data and local logs.
