ClawHub
Back to skill

Security audit

GitHub

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed GitHub/Maton integration with sensitive but purpose-aligned OAuth, API, and automation capabilities that require user approval for writes and persistent workflows.

Install only if you intend to use Maton as a gateway to GitHub. Review OAuth scopes during connection, confirm every write or automation step, keep triggers narrowly scoped, and avoid third-party trigger destinations unless you explicitly approve the host and data flow.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The GitHub skill manifest says the skill is for GitHub API integration and states that other app endpoints need to be explicitly requested by name. This file documents Slack event triggers, including Slack message and reaction payloads and trigger scoping, which is behaviorally outside the GitHub integration the skill claims to cover.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.