Undeclared Tool Scope
- 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 local design-review checker with no evidence of hidden data access, network use, or automatic persistence.
Install only if you want a lightweight local checker for structured design documents. Review its scoring rules before relying on pass/fail decisions, because they are simple heuristics rather than a full architecture review.
Without declared permissions the skill's intent is opaque and cannot be validated.
The skill is described in very broad terms as a generic design gate checker with multiple use cases and no clear trigger boundaries, exclusions, or least-privilege constraints. Overly generic invocation criteria can cause the agent to apply the skill in unintended contexts, increasing the chance of inappropriate activation, overreach, or misuse alongside whatever tools the implementation may expose.
This code includes natural-language string literals exclusively in Chinese for titles, descriptions, and component names. Under the policy, forcing a specific language without opt-in or documenting a justified locale-specific scope can be a language/locale policy violation, and no such justification appears in this file.