Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a small verification aid that reads user-selected files for fake-success patterns and does not show hidden, persistent, network, credential, or destructive behavior.
Installers should understand that this is a static heuristic scanner, not proof that code actually works. It is reasonable to use on files you choose, but review its flags manually and do not treat a clean scan as a security or correctness guarantee.
Without declared permissions the skill's intent is opaque and cannot be validated.