ClawHub
Back to skill

Security audit

Firecrawl Build Interact

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Firecrawl integration guide for browser interaction workflows, with no bundled executable code or hidden installation behavior.

Before installing, understand that /interact workflows may send page content, entered form data, and authenticated-session-derived data to Firecrawl or a configured Firecrawl backend. Use the narrowest workflow possible, avoid highly sensitive sites unless you have approval, and prefer self-hosted or tightly scoped deployments where appropriate.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly promotes Firecrawl /interact for clicks, form fills, pagination, and authentication-aware flows, but it does not warn users that these actions may execute within an authenticated browser context and send page content, form inputs, and session-derived data to Firecrawl. This omission can cause developers or agents to use the skill in sensitive contexts without understanding the privacy and credential-exposure implications, increasing the chance of unintended data disclosure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.