ClawHub
Back to skill

Security audit

Pr Review Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward PR review helper that collects local or GitHub PR diffs for an AI review without hidden persistence or unrelated behavior.

Before installing, understand that the skill may show repository diffs to the reviewing agent and, for --pr, uses your existing gh authentication to fetch a PR diff. Use it only in repositories and GitHub contexts where that code access is intended.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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)

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/pr_review.py (reported line 10)May include surrounding context.

python
import sys

def run(cmd):
    r = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
    return r.stdout.strip(), r.returncode

def get_diff(base="main", staged=False):

Static analysis

No suspicious patterns detected.