ClawHub
Back to skill

Security audit

agentpmt-docs-and-content

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AgentPMT-only search helper that sends user-directed search queries to AgentPMT public catalog and content endpoints.

Install this only if you want your agent to search AgentPMT’s public site/catalog through AgentPMT APIs. Treat search text as data sent to AgentPMT, keep queries narrow, and do not include account secrets, wallet keys, mnemonics, signatures, or payment headers in prompts or 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
85% confidence
Finding
The skill declares broad activation phrases such as searching the AgentPMT website for anything relevant, which can cause over-triggering in situations where a narrower or safer tool should be used. In an agentic system, ambiguous routing increases the chance of unnecessary external calls and unintended disclosure of user prompts or context to the remote search service.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.