ClawHub
Back to skill

Security audit

Pixmind WeChat Creator

Security checks across malware telemetry and agentic risk

Overview

This skill coherently creates WeChat articles through Pixmind's content service and discloses its API, credit, credential, and no-publishing boundaries.

Install only if you are comfortable sending article briefs, source URLs, and any provided materials to Pixmind's content service and spending Pixmind API credits after approval. Review the generated article yourself before copying it into WeChat; the skill is designed not to publish or request WeChat account credentials.

SkillSpector

By NVIDIA
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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding
The skill declares no explicit permissions while instructing the host to use networked API calls and, in fallback mode, access an environment variable for authentication. This mismatch can hide the skill's true capabilities from reviewers and users, weakening least-privilege controls and making unauthorized outbound requests or secret-dependent execution easier to overlook.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The description is broad enough to trigger the skill for many article-related requests without clearly limiting scope, user intent, or required context. In an agent environment, ambiguous invocation rules can cause the system to route unrelated or sensitive content-generation and review tasks to this skill, increasing the chance of unintended data handling or misuse of a private content engine.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/wechat-creator.js:6