ClawHub
Back to skill

Security audit

agent-guild-trust

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed trust and payment-verification helper for agent-to-agent work, with high-impact financial workflows that users should configure carefully.

Install only if you want your agent to consult Agent Guild for delegation, reputation, receipts, escrow, or x402/crypto payment decisions. Review wallet and payment approval settings separately, because the skill describes paid decision checks and high-value protection tiers; keep API keys and wallet keys out of prompts and logs.

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
79% confidence
Finding
The `operation` input description is very broad and bundles multiple security-sensitive actions such as vetting identities, gating payments, escrow, recording outcomes, and issuing signed receipts into a single free-form trigger. In agentic systems, overly broad trigger language can cause unintended invocation on loosely related requests, leading to trust decisions or payment-related actions being initiated with insufficient scoping or validation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.