ClawHub
Back to skill

Security audit

workflow-setup

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward GitHub Actions workflow helper, with only a minor risk that broad trigger phrases could activate it for generic testing or automation requests.

Before installing, be aware that the skill may be invoked by broad testing or automation wording, so review proposed workflow changes before accepting them, especially publish or deploy workflows. The artifact itself is markdown-only and does not install scripts or run background components.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list contains broad, natural-language phrases such as "testing," "automation," and "setting up automation for a Python, Rust, or TypeScript project" that can match many ordinary user requests unrelated to explicitly invoking this skill. In an agentic environment, this increases the chance of unintended auto-activation, causing the skill to propose or create CI/CD workflow files in contexts where the user did not specifically request repository automation changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.