ClawHub
Back to skill

Security audit

Stannp

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Stannp connector that can read, create, and delete Stannp recipient data, with clear confirmation requirements for changes.

Install this only if you want Codex to operate your connected Stannp account through OOMOL. Review exact payloads before approving create, update, remove, or delete actions, especially because recipient records can contain postal address data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill declares it should be used for ANY Stannp request, including read, write, and destructive operations, without narrowing when the skill should or should not be invoked. This broad trigger scope can cause over-selection of the skill and increases the chance an agent routes sensitive or destructive Stannp tasks through it without sufficient contextual gating beyond the prose safety notes.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.