Contributor Guide Writer

Security checks across malware telemetry and agentic risk

Overview

This appears to be a contributor-guide helper whose main risk is ordinary workspace file creation, not malicious behavior.

Install only if you want the agent to help create or update contribution documentation. Before running it, ask the agent to show the planned CONTRIBUTING.md changes or a diff, especially if the repository already has that file.

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 (2)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The README states that the skill will automatically generate a CONTRIBUTING.md file, but it does not clearly warn users that this creates or overwrites a file in the workspace. In an agent setting, implicit file modification can lead to unintended repository changes, especially if the user expected analysis or advice rather than a write action.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger description is broad enough to activate on general requests about local setup or project understanding, not just explicit requests to generate a CONTRIBUTING.md file. This can cause the skill to run in unintended contexts, leading to over-collection of repository context and responses that do not match user intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal