ClawHub
Back to skill

Security audit

iFlow Search

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward iFlow search wrapper, with the main caution that searches, URLs, and an iFlow API key are used with an external service.

Install only if you trust iFlow with your search terms, image queries, fetched URLs, and API-key-backed requests. Avoid submitting secrets, private document links, localhost or internal-only URLs, and consider storing IFLOW_API_KEY in a secret manager or temporary shell environment instead of a persistent shell startup file.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill explicitly requires and demonstrates use of shell tooling (`bash`, `curl`) but does not declare corresponding permissions or present clear execution constraints. This creates a transparency and policy gap: an agent may invoke shell-backed actions without users or the platform having an accurate understanding of the skill's capabilities, increasing the chance of unintended command execution or overbroad trust in the skill.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The invocation examples are framed around broad, ordinary user requests like searching news, finding images, or reading a webpage, without clear boundaries on when the skill should activate. In agent environments, this can cause over-triggering, sending user queries or URLs to external services in situations where the user did not meaningfully consent to web/API use.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The description explains functionality but does not clearly warn that user search terms and supplied URLs are transmitted to the external iFlow Search API. This omission can lead to inadvertent disclosure of sensitive prompts, internal URLs, tokens embedded in links, or other private data to a third-party service.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script transmits a user-supplied URL to a third-party service without any explicit warning, consent prompt, or indication that the target URL will leave the local environment. This can expose sensitive internal URLs, private document links, or user browsing targets to the external iFlow API, which is a real privacy and data-handling risk even if the feature is intentional.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.