ClawHub
Back to skill

Security audit

Export Http Postman

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Postman export helper with disclosed project scanning, output-file creation, and local domain-memory behavior.

Before installing, be aware that the skill will inspect your project to infer routes and may save service-domain mappings for reuse. Review references/domains.md if generated Postman base URLs matter, and avoid approving exports that would include real tokens, cookies, or other secrets.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill instructs the agent to read project files, write output JSON, persist data into `references/domains.md`, and potentially consult external domains, but no explicit permission declaration is present. This creates a capability/permission mismatch that can lead to over-privileged execution, unexpected file modification, and possible network access without clear user or platform visibility.

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding
The advertised purpose is endpoint export, but the skill also maintains durable memory by reading and writing service-domain mappings in `references/domains.md`. That hidden statefulness changes the trust model: a user invoking a simple export may unknowingly cause persistent data modification, and future runs may consume attacker-poisoned mappings to generate incorrect or sensitive destinations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.