ClawHub
Back to skill

Security audit

Code Review Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward code-review guidance skill with no hidden execution, persistence, or unrelated data access.

Install this only for repositories where you are comfortable letting the agent inspect diffs and related review context. The skill does not appear to run code or persist changes by itself, but GitHub/GitLab CLI use may expose PR contents available to your local credentials.

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
  • 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)

Unbounded Resource Access

Medium
Category
Excessive Agency
Content
- Missing or incorrect caching
- Unnecessary allocations in hot paths
- Blocking operations in async contexts
- Missing pagination or unbounded queries
- Inefficient algorithms (quadratic loops on large data)

**Pass 4 — Maintainability:**
Confidence
80% confidence
Finding
Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.

Static analysis

No suspicious patterns detected.