ClawHub
Back to skill

Security audit

WCAG Accessibility — Testing, Fixing, and Building Accessible Pages

Security checks for vulnerabilities and agentic risk

Overview

This accessibility skill needs review because its mandatory testing instructions cover payments, legal commitments, and record changes without clear safe-testing boundaries.

Use staging sites, synthetic records, and sandbox payments for consequential tests. Require explicit authorization before any live transaction, legal commitment, or record change. Keep Chrome sandboxing enabled unless running in an isolated CI environment, and verify dependency versions before installation.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The protocol instructs testers to exercise high-impact submission paths without a safe-testing warning.

Medium
Category
Output Handling
Confidence
86% confidence
Finding

The protocol directs testers to exercise confirmation and reversal paths for financial transactions, legal commitments, and data changes without requiring an isolated environment or authorization for consequential actions. On a live service, following these instructions could create real transactions or modify records, and a reversal may not undo every consequence. These tests are legitimate accessibility work, but their context requires explicit safe-testing boundaries.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.