ClawHub
Back to skill

Security audit

GitHub Actions Workflow Generator

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill for generating GitHub Actions workflow YAML, with only minor caution around broad activation wording and deployment-capable templates.

Before installing, confirm you want generic CI/CD requests to route to a GitHub Actions generator. Review any generated deploy or release workflow before committing it, especially permissions, secrets, environments, cloud role names, and third-party actions.

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)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger keywords are broad enough to match many generic CI/CD or workflow conversations, which can cause this skill to activate outside its narrow intended context. In an agentic system, overbroad invocation can lead to inappropriate repository scanning, generation of deployment workflows, or unsolicited security-sensitive guidance in contexts where the user did not explicitly request this skill.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation guidance includes ambiguous conditions like wanting to 'automate my deployment' or 'set up CI', which are broad requests that may apply to many tools beyond GitHub Actions. This increases the chance of the skill being invoked in the wrong context, leading to mismatched automation advice or generation of deployment-capable workflows without sufficiently specific user intent.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.