Security audit

Sg

Security checks for vulnerabilities and agentic risk

Overview

This GitHub automation skill is not deceptive, but it asks for broad, high-impact repository powers without enough guardrails.

Install only if you intend to give an agent broad GitHub repository automation abilities. Use a least-privilege GitHub token, keep secrets and workflow changes behind explicit user approval, and review release or tag operations before running them.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

High

Confidence: 98% confidence
Finding: The skill explicitly advertises the ability to get/set repository secrets without any warning, approval requirement, or handling guidance. Secret access and modification are highly sensitive operations that can expose credentials, enable persistence, or break CI/CD security if invoked by an agent without strict safeguards.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The skill is described as an 'ultimate GitHub automation framework' with broad repository-management capabilities but no clear activation boundaries, permission limits, or task constraints. In an agent setting, this ambiguity can lead to overbroad use of powerful GitHub actions in situations the user did not explicitly intend, increasing the chance of unintended repository changes or sensitive operations.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The documentation includes workflow management and release automation capabilities that can materially change repository behavior, deployment processes, and published artifacts, yet it provides no caution about their impact. In an automation skill, these actions can trigger CI/CD runs, alter software delivery, or publish incorrect or malicious releases if used without explicit controls.