Back to skill

Security audit

Kiwi Design System

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates the kiwi-design-system skill benign with high confidence: the completed scan found no AIG issues, and its one low-probability Skillspector flag was judged expected for the skill’s purpose.

The verdict is benign with high confidence, and all four listed components were fully inspected. The scan found one low-probability wording concern that it judged expected; benign does not mean risk-free, so review the skill’s instructions and decide whether they fit your needs before installing.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 94)May include surrounding context.

md
Report the source revision, checks actually run, related PRs, and what remains.
Distinguish design-system merge, npm publication, and consumer adoption. A
contribution request does not itself authorize publishing packages or deploying
the app. Follow already authorized release scope without asking again.