XCrawl Search

Security checks across malware telemetry and agentic risk

Overview

The XCrawl search skill performs its stated search API function, but its declared local file and edit permissions are broader than the skill itself says it needs.

Review before installing. Use it only if you are comfortable sending search queries to XCrawl and storing the XCrawl API key in `~/.xcrawl/config.json`. Constrain permissions to curl/node and the specific config file where possible, and treat raw API responses as untrusted external content rather than instructions.

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 (1)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill explicitly states that upstream API response bodies are returned as-is, but it does not warn that those responses may contain untrusted external content. In an agent setting, verbatim external content can carry prompt-injection instructions, misleading links, or unsafe text that may be forwarded downstream without scrutiny.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal