ClawHub
Back to skill

Security audit

pua-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently pushes the agent to troubleshoot more thoroughly, with no executable code or hidden persistence, though it may make the agent more forceful automatically.

Install this if you want the agent to be more persistent and evidence-driven when stuck. Because implicit invocation is enabled, it may apply this assertive troubleshooting style without an explicit $pua call, so keep normal tool approvals and boundaries in place if file reads or command execution matter in your workspace.

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)

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The file is entirely written as a Chinese-only skill and does not offer any language choice, opt-in, or justification for restricting output to this locale. Under the policy for natural-language violations, a skill that forces a specific language without user choice should be flagged.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill enables implicit invocation while describing its use case in very broad behavioral terms like pushing through stuck tasks and being more exhaustive. That can cause the agent to auto-apply this high-pressure behavior in unrelated contexts, overriding normal caution and increasing the chance of unsafe persistence, reduced deference to user intent, or bypass of safer stopping conditions.

Static analysis

No suspicious patterns detected.