ClawHub
Back to skill

Security audit

Http Sec Audit

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward security-header checker that makes user-directed web requests and reports results locally.

Install only if you want an agent to contact websites for header checks. Use it against sites you own or are authorized to audit, and avoid localhost, internal network, metadata-service, or otherwise sensitive URLs unless you intentionally want the agent environment to request them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill clearly performs outbound network access by auditing arbitrary URLs, but the metadata shown does not declare any corresponding permission. Undeclared network capability is a security issue because it weakens platform trust boundaries, prevents accurate policy enforcement, and may allow unexpected external requests or scanning behavior under the guise of a benign audit skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.