ClawHub
Back to skill

Security audit

Implement Issue

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Gitee issue-to-PR workflow, but users should review any comments, pull requests, or issue status updates before they are posted.

Install this only if you want an agent to work with a specific Gitee issue and local repository checkout. Use a least-privilege Gitee MCP account, confirm the repository path, and review generated comments, pull request text, and issue status changes before they are submitted.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger phrases are broad enough to match common development requests such as 'work on this issue' or 'implement issue', which can cause the skill to activate in situations where the user did not clearly consent to Gitee-side actions. In this skill's context, activation can lead to external side effects like posting issue comments or creating PRs, making accidental invocation materially risky.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs the agent to post issue comments, create a PR, and update issue state without an explicit user-approval checkpoint immediately before those side-effecting actions. This increases the chance of unintended repository modifications, noisy comments, premature PRs, or disclosure of implementation details to collaborators when a user only asked for analysis or coding help.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.