ClawHub
Back to skill

Security audit

知识资产化巧匠

Security checks for vulnerabilities and agentic risk

Overview

This skill converts user-provided documents into structured knowledge-base files, and its file access is disclosed and aligned with that purpose.

Install only if you want a workflow that reads user-selected source documents and creates structured knowledge-base outputs. Review inputs for confidential or personal data first, and confirm the destination files before generating JSONL or Markdown outputs.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
81% confidence
Finding
The skill explicitly instructs use of local scripts and file processing workflows (`scripts/doc_reader.py`, `scripts/validate_dual_view.py`) but does not declare permissions for file read/write. Hidden or undeclared filesystem access weakens the trust boundary: operators may approve the skill believing it is documentation-only, while it can in practice access or modify local artifacts involved in knowledge-base generation.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger list includes broad phrases like '结构化一下', '做知识卡片', and '内容结构化', which can cause accidental activation on unrelated user requests. In a skill that handles source documents and may read/write files, overbroad invocation increases the chance of unintended document processing, data exposure, or workflow confusion without clear user intent.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The description claims applicability to 'any raw material' and many fuzzy utterances, leaving activation boundaries unclear. Ambiguous scope is risky because this skill is positioned to ingest large, potentially sensitive corpora; if invoked too broadly, it may process content the user did not intend to entrust to this workflow.

Static analysis

No suspicious patterns detected.