ClawHub
Back to skill

Security audit

GitHub Actions Troubleshooting

Security checks for vulnerabilities and agentic risk

Overview

This skill provides straightforward GitHub Actions troubleshooting guidance with only expected GitHub CLI and Go workflow commands.

Installers should be comfortable with the skill using the GitHub CLI against repositories they specify. When downloading workflow artifacts, use an isolated directory, review artifact names and sources, avoid directly running downloaded scripts or binaries, and delete artifacts when no longer needed.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
86% confidence
Finding
The skill recommends `gh run download <run-id> --repo owner/repo` without cautioning that workflow artifacts are untrusted output from CI and will be written to the local filesystem. Artifacts can contain sensitive repository/build data or deceptive files that a user may later open or execute, so the omission creates a low-severity safety gap rather than direct code execution by itself.

Static analysis

No suspicious patterns detected.