ClawHub
Back to skill

Security audit

AI Agent Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a small Markdown-only skill for helping design AI-agent prompts and workflows, with no code execution, data access, persistence, or hidden behavior found.

Install only if you want agent/prompt-design help in the language style shown. Review outputs for fit before applying them to sensitive agents, because the skill gives general agent-design patterns rather than strict safety boundaries.

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
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill description is written in a specific language style without indicating that the user can choose another language or locale. This can cause the skill to respond in an unintended language, reducing clarity, causing misconfiguration, or making safety-critical instructions harder for the user to verify.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The invocation examples are very broad and do not define when the skill should or should not activate. In an agent environment, vague triggers can cause over-invocation, prompt hijacking of unrelated tasks, or accidental application of agent-design guidance in contexts where it was not requested, increasing the chance of unsafe or misleading behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.