ClawHub
Back to skill

Security audit

Phy Schema Sleuth

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill helps generate schemas from user-provided sample data and does not include hidden code, external execution, persistence, or credential handling.

Installers should be aware that the broad trigger phrases may activate the skill for general schema or type-generation requests. Avoid pasting secrets or regulated data as samples unless you are comfortable having the assistant analyze that content.

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
92% confidence
Finding
The metadata description embeds numerous natural-language trigger phrases such as 'generate schema', 'generate types', and 'what's the schema for', which are common in normal developer conversation. This makes accidental invocation plausible in unrelated contexts, potentially causing the skill to activate on arbitrary pasted data and influence outputs when the user did not explicitly intend to use it.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The dedicated trigger list contains broad phrases like 'infer schema', 'generate types', 'model this data', and 'parse this data format' without scope constraints. In a developer assistant environment, these phrases are common enough that the skill could be invoked unintentionally, causing prompt-routing confusion and exposing user-provided data to unintended processing logic.

Static analysis

No suspicious patterns detected.