ClawHub
Back to skill

Security audit

p3c-code-quality

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a disclosed Java/P3C code-quality review and writes a Markdown report, with no evidence of hidden execution, credential access, or persistence beyond the report file.

Before installing, expect the skill to read the Java files you ask it to inspect and create a Markdown report inside the repository under doc/{business}/测试报告/{test_content}/. Review or configure the output path if you want to avoid generated files appearing in commits.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
85% confidence
Finding
The rule `注释语言应与项目一致（中文项目用中文）` imposes a language requirement in the skill's natural-language policy text. The file does not indicate that users can choose another language/locale or that this locale restriction is an opt-in, region-specific requirement.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The skill explicitly plans to use the `Write` tool to generate Markdown reports inside the workspace, but it does not clearly warn the user up front that running the skill will create or modify repository files. This can lead to unexpected file creation, repository pollution, or accidental inclusion of generated artifacts in commits, especially when users assume the skill is read-only analysis.

Static analysis

No suspicious patterns detected.