ClawHub
Back to skill

Security audit

gh-modify-pr

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward GitHub PR-review helper that may clone, edit, and locally commit code, with pushing left to explicit user approval.

Install this only if you are comfortable letting the agent use your GitHub CLI authentication to read PR details, clone or open the repository, edit code, and create a local commit. Review the diff before approving any push.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger phrase "update this PR" is broad enough to match common, underspecified user requests and could activate a skill that performs repository checkout, code modification, and local commits without sufficiently clear user intent. In this skill's context, the ambiguity is more dangerous because activation leads directly to high-impact actions on source code and git state, even if push requires later approval.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.