ClawHub
Back to skill

Security audit

Coding Net

Security checks across malware telemetry and agentic risk

Overview

This skill coherently supports user-directed Tencent Coding DevOps queries and issue creation, but users should treat the required Coding token as sensitive.

Install only if you intend to let the agent access your Tencent Coding workspace and create issues when you ask it to. Prefer setting CODING_TOKEN in the environment instead of pasting it into chat, use the least-privileged token available, and review any create_issue call before it runs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
This markdown file tells the agent to check for a token in the user's message or environment and to ask the user to provide a Coding personal access token. While it explains how to obtain and validate the token, it does not warn the user that this credential is sensitive and grants API access, nor advise safe handling or limiting exposure.

Env Variable Harvesting

High
Category
Data Exfiltration
Content
def _resolve_token(token: str | None) -> str:
    if token is not None and token.strip():
        return token.strip()
    env = os.environ.get(TOKEN_ENV, "").strip()
    if env:
        return env
    raise ValueError(
Confidence
70% confidence
Finding
os.environ.get(TOKEN

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.