ClawHub
Back to skill

Security audit

repair-agent

Security checks for vulnerabilities and agentic risk

Overview

This skill is a repair workflow guide that may lead an agent to edit code and run tests, but that behavior matches its stated bug-fixing purpose and no hidden or unrelated behavior was found.

Install this only if you want an agent to help diagnose bugs, propose or apply patches, and run project tests. Use version control and review changes before accepting them, especially in large or side-effect-heavy projects.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill is explicitly designed to perform autonomous bug fixing, patch generation, and test validation, which reasonably implies editing repository files and executing tests or related commands in the user's workspace. Omitting a clear warning about code modification and command/test execution can cause users to invoke the skill without understanding that it may change files, consume resources, or trigger side effects in local or CI-like environments.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file contains code examples that apply and revert patches and execute tests, which are safety-relevant actions affecting user code and potentially the local environment. The surrounding markdown provides no warning or disclosure that the example performs temporary code modifications and test execution.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.