ClawHub
Back to skill

Security audit

code-review-skill

Security checks for vulnerabilities and agentic risk

Overview

This is a broad code-review checklist that may encourage wider code and test changes, but it does not show hidden, credential, network, persistence, or destructive behavior.

Install only if you want a skill that can push the agent toward comprehensive staged-change review with suggested fixes and tests. Review generated edits before applying them, especially in large repositories, because the skill does not define tight limits on how much code or test implementation to propose.

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
92% confidence
Finding

The skill consists of a broad, generic instruction to perform a comprehensive code review and add tests, without any clear trigger conditions, repository scope limits, or safety constraints. Such open-ended wording can cause the skill to activate in unintended contexts and drive high-impact actions like proposing complete code and test implementations beyond the user's intended request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.