ClawHub
Back to skill

Security audit

sn-search-image

Security checks across malware telemetry and agentic risk

Overview

This skill coherently provides a Serper-backed image search helper, with a minor dependency hygiene issue but no hidden or purpose-mismatched behavior found.

Before installing, confirm you are comfortable providing a SERPER_API_KEY and sending search queries to Serper.dev. The publisher should remove or pin the unused requests dependency, but the inspected behavior is narrowly scoped to image search.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests
Confidence
98% confidence
Finding
The dependency is unpinned, so installs may pull different versions over time, including unexpectedly broken or newly vulnerable releases. In a skill that makes outbound web requests for image discovery, dependency drift can affect both security posture and runtime behavior.

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High
Category
Supply Chain
Confidence
95% confidence
Finding
The file explicitly depends on requests without constraining it to a patched version, and the scanner reports multiple known advisories affecting that package. Because this skill performs network access against external services and may handle URLs returned from search results, vulnerable HTTP client behavior could expose credentials, weaken request validation, or otherwise increase risk when interacting with malicious or crafted endpoints.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.