GitHub操作助手

• Outcome: Review
• Latest audit: May 28, 2026, 12:23 PM
• Version:
  2.0.0

Overview

This GitHub helper is purpose-aligned, but it gives agents examples for merging PRs and closing issues without clear confirmation or repository scoping guidance.

Install only if you are comfortable with an agent using your logged-in GitHub CLI context. Before allowing merges, issue closures, releases, or comments, require explicit repository, PR or issue number, and a confirmation step.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The activation phrases are broad enough to trigger on ordinary GitHub-related conversations, which can cause the skill to activate unexpectedly in contexts where the user did not intend repository-affecting actions. In a skill that includes PR merges, issue closure, and repo operations, overbroad activation increases the chance of accidental or unauthorized high-impact actions.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill exposes destructive operations like merging PRs and closing issues without warning, confirmation, or safety guidance. In an agent setting, this raises the risk of irreversible or workflow-disrupting actions being taken from ambiguous instructions or accidental invocation.

VirusTotal

64/64 vendors flagged this skill as clean.