ClawHub
Back to skill

Security audit

DHgate

Security checks for vulnerabilities and agentic risk

Overview

This is a local, instruction-only DHgate shopping workflow that asks before saving notes and contains no code or network access.

Before installing, decide whether you want the skill to step in only for explicit DHgate requests or also for adjacent import/sourcing topics. Only approve local saving in ~/dhgate/ if you want persistent buying notes, and avoid storing payment, identity, or tax details there.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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
Findings (2)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · supplier-vetting.md (reported line 11)May include surrounding context.

md
| Area | 0 | 1 | 2 |
|------|---|---|---|
| Store maturity | brand-new or unclear history | some history but limited proof | multi-year store with visible trading history |
| Listing clarity | vague specs, thin photos, contradictions | mostly clear with some missing details | exact specs, dimensions, variants, and useful photos |
| Review realism | generic praise only | mixed quality, limited evidence | detailed reviews with real-world photos and specifics |
| Price sanity | far below comparable offers | slightly below market without explanation | price fits the range after quantity and shipping are considered |

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs broad proactive activation for generic topics like wholesale listings, cheap marketplace deals, import buying, and disputes, which can cause the agent to engage outside a narrowly intended DHgate context. Overbroad triggering increases the chance of unintended data collection, user confusion, and inappropriate intervention in unrelated commerce conversations, especially because the skill also asks to confirm activation behavior within the first exchanges.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.