GitHub PR Writer

Security checks across malware telemetry and agentic risk

Overview

This skill is a small, instruction-only helper for drafting GitHub pull request descriptions and does not show hidden code, persistence, destructive actions, or data exfiltration.

Install this if you want help writing PR descriptions. Review the generated PR body before posting, especially if your branch diff or commit messages include sensitive details, and confirm the target repository and branch before allowing any GitHub CLI action.

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 (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger condition "when a branch is ready to merge" is overly broad and can cause the skill to activate in many contexts beyond an explicit request to write or update a PR description. In an agent setting, broad activation increases the chance of unintended execution, context hijacking, or the model taking action based on weak signals rather than clear user intent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal