Back to skill

Security audit

kb-distiller

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: the completed AIG scan reported no findings, while Skillspector found limited concerns about undeclared tool scope and fixed Chinese-language output; its review was partial because one referenced path was missing.

The verdict is benign, not risk-free. Before installing, consider whether you are comfortable with the reported file and network capabilities and fixed Chinese-language output. Skillspector inspected all listed components but marked its analysis partial because a referenced path was missing; AIG completed with no findings.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The manifest fixes the skill's language to Simplified Chinese without a documented user choice.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The configuration sets "language" to "zh-CN" without offering a user opt-in or language override. Documentation generation is not inherently region-specific, and the file provides no justification for imposing this locale.

Content

No source excerpt is available for this finding.

The manifest fixes the skill language to Simplified Chinese without user opt-in.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The language setting explicitly selects zh-CN, with no user language choice or opt-in provided. The React development domain does not establish a locale-specific justification for this restriction.

Content

No source excerpt is available for this finding.

The manifest fixes the skill language to Simplified Chinese without user opt-in.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The configuration sets language to zh-CN without providing a user language choice or opt-in. The general UI/UX design scope does not document a regional requirement that justifies this locale restriction.

Content

No source excerpt is available for this finding.

Defaults generated knowledge files to Chinese without explicit user language opt-in.

Medium
Category
Output Handling
Confidence
87% confidence
Finding

The instruction makes Chinese the default output language when the domain configuration does not specify one. Although configuration can override this default, the skill does not explicitly offer the user a language choice or justify the locale restriction.

Content

No source excerpt is available for this finding.

The style rules require Chinese body text without offering a language choice or explaining why Chinese is required.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

The instruction “中文正文、API 名/术语/报错保留英文原文” explicitly mandates Chinese prose while preserving API names, terminology, and error messages in English. The file provides neither user opt-in nor a documented locale-specific justification for this requirement.

Content

No source excerpt is available for this finding.