ClawHub
Back to skill

Security audit

Phy A11y Reviewer

Security checks for vulnerabilities and agentic risk

Overview

This is a static accessibility review checklist with no executable code, credential handling, persistence, or hidden data access.

Install this if you want a Chinese-language WCAG accessibility review checklist and report format. Be aware it may activate on broad accessibility-related terms, so users who prefer another language or narrower activation may want the publisher to add clearer language handling and more specific triggers.

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 (2)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger list includes broad terms like "accessibility" and "WCAG", which can appear in many normal conversations and contexts unrelated to invoking this skill. That can cause unintended auto-activation, leading the agent to take over responses or apply the skill in situations where the user did not clearly request an accessibility audit.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The skill metadata and body are written to operate in Chinese without offering language selection, which can override or conflict with the user's preferred language. While not a classic security flaw, it can reduce transparency, impair user understanding of the skill's actions and findings, and increase the chance of misinterpretation in mixed-language environments.

Static analysis

No suspicious patterns detected.