ClawHub

jd-affiliate

Security checks across malware telemetry and agentic risk

Overview

The skill appears purpose-aligned for JD affiliate work, but it handles private earnings or withdrawal-related affiliate data without clear consent boundaries and has broad activation triggers.

Install only if you intend to use JD affiliate account features. Treat commission, settlement, withdrawal, and earnings outputs as sensitive financial/account data, and avoid invoking those workflows unless you have explicitly asked for them and trust the publisher with the connected account.

SkillSpector

By NVIDIA
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
Confidence
91% confidence
Finding
The trigger conditions are broad enough to activate on generic mentions like '京东推广' or '京粉', which can cause the skill to engage outside the user's actual intent. In an affiliate context, unintended invocation can steer conversations toward link generation, commission lookup, or promotional workflows without clear user consent, increasing the risk of misrouting, privacy mistakes, or inappropriate commercial actions.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The skill handles affiliate functions such as commission queries, settlement records, withdrawals, and earnings statistics, but it does not warn users that these actions may involve sensitive account or financial data. Without clear user-facing notice and consent boundaries, users may unknowingly expose private affiliate information or trigger access to account-linked data in a context that feels like a generic product query.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal