ClawHub
Back to skill

Security audit

GitHub Triage

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for GitHub triage, but it asks users to install and globally enable an external plugin that handles GitHub OAuth-backed actions without pinning or documenting exact scopes.

Install only if you trust ClawLink and are comfortable granting it GitHub access. Before connecting GitHub, check the OAuth scopes, limit repository access if GitHub offers that option, and know how to revoke the ClawLink grant and remove the plugin later.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:57
Finding

Unpinned Third-Party Plugin Installation Expands the Trusted Supply Chain

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 181)May include surrounding context.

md
## Triage Operations

### Read Operations (Safe — no confirmation needed for read-only triage)

| Tool | Description |
|------|-------------|

Static analysis

No suspicious patterns detected.