XCrawl Scrape

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate XCrawl scraping helper, but it needs review because it can send sensitive request data to a third party and declares broader local file permissions than its workflow needs.

Review before installing. Use it only for URLs and page data you are comfortable sending to XCrawl, avoid session cookies, authorization headers, internal-only URLs, and secrets unless you intentionally want XCrawl to receive them, protect ~/.xcrawl/config.json, and consider narrowing the allowed tools to curl/node plus only the local config access actually required.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents request fields such as cookies, headers, webhook URLs, and target URLs that are sent to XCrawl, but it does not clearly warn that this data is transmitted to an external third-party service. This can cause users to unknowingly send sensitive session material or internal URLs off-platform, increasing privacy, credential, and SSRF-style exposure risks.

Missing User Warnings

Low
Confidence
89% confidence
Finding
The skill instructs users to store an API key in a local config file but does not include guidance on secure credential handling such as file permissions, avoiding source control, or preventing accidental disclosure in logs. While this is common operational guidance, omitting basic safeguards can lead to credential leakage through misconfiguration or unsafe sharing of the config file.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal