ClawHub
Back to skill

Security audit

GitHub操作助手

Security checks for vulnerabilities and agentic risk

Overview

This GitHub helper is purpose-aligned, but it gives agents broad authenticated GitHub mutation examples without clear confirmation or scoping safeguards.

Install only if you are comfortable with an agent using your logged-in GitHub CLI session. Before using it, prefer a least-privilege GitHub account or token, verify the target repository for every command, and require explicit confirmation before PR merges, issue closures, releases, or other write actions.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation phrases are very broad (e.g. generic GitHub/PR/Issue terms), which can cause the skill to trigger in situations where the user did not explicitly intend to invoke it. Because this skill supports authenticated and state-changing GitHub actions such as creating, merging, and closing resources, accidental invocation can lead to unintended repository operations under the user's credentials.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill documents authenticated gh CLI usage and multiple state-changing operations but does not warn users that these actions can modify remote repositories, issues, and pull requests using the currently logged-in GitHub identity. In this context, missing warnings and safeguards increase the chance of destructive or unauthorized-seeming actions being taken without informed user consent, particularly when combined with broad activation and automation use cases.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.