ClawHub
Back to skill

Security audit

Agent Render Linking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent link-rendering helper, but users should avoid using it for secrets or private artifacts unless they intend to share them.

Install only if you want agents to turn artifacts into shareable agent-render.com links. Do not use it for secrets, credentials, confidential code, private customer data, or other sensitive content unless sharing that URL is intentional; for sensitive workflows, prefer a self-hosted viewer or ask the agent to confirm before generating the link.

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 trigger description uses broad natural-language phrases such as 'share this as a link' and 'render this markdown/code/csv/json', which are common in ordinary conversation and can cause the skill to activate in situations the user did not explicitly intend. Because this skill packages arbitrary artifact content into external browser links on a third-party domain, over-broad invocation increases the chance of unintended data disclosure or unnecessary exfiltration of sensitive content into a URL fragment.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.