ClawHub
Back to skill

Security audit

demo

Security checks for vulnerabilities and agentic risk

Overview

This is a simple document-summary skill that reads user-provided text and returns Markdown, with only a minor risk that broad trigger wording could invoke it too often.

This appears safe to install for document summarization. Be aware that generic prompts like analyzing text may select this skill, so only provide sensitive content when you intend it to be summarized in the current session.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation guidance is overly broad: phrases like "summarize a document," "analyze text," or "extract key points" are common user intents and could cause the skill to trigger in situations where a more specific tool or workflow was intended. This increases the risk of accidental invocation, unintended data exposure to the skill context, or interference with other skills, though the skill itself does not contain obviously dangerous behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.