ClawHub
Back to skill

Security audit

Firecrawl

Security checks for vulnerabilities and agentic risk

Overview

The Firecrawl skill is mostly coherent, but it asks the agent to run an unverified remote installer script if the required CLI is missing.

Review the setup path before installing. Prefer installing the oo CLI from verified official documentation, and do not allow an agent to run the remote installer automatically unless you trust OOMOL's installer source and accept the account-level Firecrawl actions this skill can perform.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill includes a classic remote-script execution pattern: downloading an installer with curl and piping it directly to bash. If the remote server, transport path, or installer content is compromised, the agent or user could execute arbitrary code with the current user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger text says to use this skill for ANY Firecrawl request and instead of calling the API directly, which is overly broad and can cause the agent to invoke the skill in situations where narrower, safer handling would be more appropriate. Broad auto-routing increases the chance of unnecessary execution of read, write, or destructive connector actions, especially when combined with shell-based execution guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.