ClawHub
Back to skill

Security audit

GitClassic

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only guide for browsing GitHub through GitClassic, with a disclosed but important third-party private-repository OAuth consideration.

Use this freely for public repositories. Before using PRO with private repositories, confirm you trust GitClassic as a third-party service, review the GitHub OAuth scopes and repository selection, and avoid granting access to sensitive or regulated repositories unless that exposure is acceptable.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly encourages access to private repositories through a third-party service using GitHub OAuth, but does not warn users that repository contents and metadata may be exposed to an external provider. In an agent context, this omission is security-relevant because users may assume GitClassic is equivalent to GitHub and authorize broad private-repo access without understanding the trust boundary.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.