ClawHub
Back to skill

Security audit

Passkey

Security checks for vulnerabilities and agentic risk

Overview

This is a focused passkey guidance skill with no executable code, persistence, or hidden system access.

This skill is appropriate as implementation guidance, but passkey authentication affects account security; users should still validate the recommendations against their framework, current WebAuthn library documentation, and their application's recovery and risk requirements before deployment.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- Transports hint — helps browser suggest correct authenticator

## Registration Traps
- `userVerification: "required"` enforces biometric/PIN — "preferred" may skip verification
- Attestation usually unnecessary — requiring it reduces device compatibility
- Allow multiple passkeys per account — users have multiple devices
- Resident key capability varies — don't assume all authenticators support discoverable credentials
Confidence
85% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.