Security audit

Firecrawl Cli

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its Firecrawl web-scraping purpose, but it automatically reads local marketing context and lacks important scoping and safety guidance.

Review before installing. Use it only for sites and data you are authorized to access, keep crawl and extraction scope narrow, and avoid collecting personal or sensitive data without a valid basis. Treat `FIRECRAWL_API_KEY` as a secret. Do not allow the skill to read local product-marketing context unless that context is actually needed and you are comfortable with it influencing prompts or outputs sent to Firecrawl.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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

Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:15
Finding: Unnecessary Access to Local Product Marketing Context
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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

Findings (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill explicitly guides users to scrape, crawl, search, and autonomously extract website content, but it does not warn about authorization, terms-of-service, robots.txt, personal data, or legal/privacy constraints. In a scraping-focused skill, that omission materially increases the chance of misuse or accidental collection of sensitive or prohibited data, especially when using broad commands like crawl, agent, and extract.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The environment setup section instructs users to export an API key directly but does not warn that the key is a secret that must not be logged, committed, echoed back in chat, or embedded in scripts. This can lead to inadvertent credential exposure during setup or troubleshooting, though the impact is narrower than the scraping-policy issue.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.