ClawHub
Back to skill

Security audit

Feature Spec Enhanced

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation helper for PRDs and optional HTML feature explainers, with no code execution, persistence, credential access, or hidden high-impact behavior.

Installers should know this skill may produce Chinese-language HTML explainers unless the user or agent adapts the output language, but the artifact shows no suspicious system access or unsafe 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
  • 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
97% confidence
Finding
The skill explicitly instructs the agent to always emit a Chinese-language self-contained HTML document, regardless of the user's language or locale. This can override user expectations, cause misleading or unusable output for non-Chinese-speaking users, and create compliance/accessibility issues when language selection is not user-driven or justified by documented context.

Natural-Language Policy Violations

Low
Confidence
87% confidence
Finding
The manifest description includes both English and Chinese text, which introduces a language-specific behavior without indicating user opt-in or choice. Under the policy rule, language or locale constraints should be explicitly optional or justified.

Static analysis

No suspicious patterns detected.