ClawHub
Back to skill

Security audit

code-reviewer

Security checks for vulnerabilities and agentic risk

Overview

This skill only gives the agent code-review guidance, with no hidden commands, persistence, or external data handling found.

Install this if you want broad code-review help. Because reviews may involve private source code, invoke it only on code you intend the agent to inspect, but the artifact itself does not add extra data access or execution behavior.

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
95% confidence
Finding

The skill description uses broad trigger phrases like 'code quality, security review, performance analysis, testing coverage, documentation' without clear scoping constraints, which can cause the agent to be invoked in many loosely related contexts. Over-broad routing increases the chance this skill is selected for untrusted or sensitive tasks, potentially exposing code, secrets, or security-relevant decisions to an inappropriately generalized workflow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.