ClawHub
Back to skill

Security audit

Superpowers Receiving Code Review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a code-review response guide with no executable code, persistence, credential handling, network access, or hidden high-impact behavior.

Install this if you want a Chinese-language workflow for handling code review feedback with verification and reasoned pushback. Non-Chinese-speaking users should be aware that the operational instructions are not bilingual, so reviewability depends on being able to read Chinese or translating the file first.

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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill content is entirely in Chinese and implicitly directs responses in that language without indicating this is a locale-specific skill or offering language choice. This can override user expectations, reduce reviewability for non-Chinese-speaking operators, and create a prompt-quality/security-policy issue where important behavioral constraints are less transparent to the broader system and reviewers.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.