ClawHub
Back to skill

Security audit

企业-招投标合规风险预警

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language procurement compliance research workflow that uses public-source searching and risk scoring without hidden code, persistence, or credential access.

Before installing, users should understand that this skill may produce reputational and compliance risk assessments about companies based on public procurement records. Use it for procurement due diligence, check cited official sources, and treat inferred internal-control conclusions as analysis rather than verified facts.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are broad enough to activate on generic due-diligence, supplier onboarding, and negative-news requests, not just narrowly scoped procurement-compliance investigations. This can cause the skill to over-collect, over-analyze, or steer ordinary business queries into a high-scrutiny workflow that produces sensitive reputational assessments without sufficiently constrained user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

All user-facing description, triggers, parameters, and instructions are in Chinese, which effectively forces one language/locale. The file does not state that the skill is limited to Chinese-speaking users or China-only workflows as a documented locale policy, nor does it offer language selection or opt-in.

Content

No source excerpt is available for this finding.