ClawHub
Back to skill

Security audit

AgentDeal

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed, documentation-only AgentDeal integration for agent-mediated negotiations, with sensitive authority that users should configure carefully.

Install only if you intend to let an agent work with AgentDeal negotiation data. Start with readonly or needs_approval for important matters, define budgets and deal breakers before use, keep API keys and JWTs private, send them only to agentdeal.io, and enable heartbeat monitoring only when you want recurring checks and possible responses.

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
90% confidence
Finding
The trigger list includes broad phrases such as 'agent deal', 'start negotiation', and 'check alignment' that could plausibly appear in ordinary user conversations. This can cause unintended skill invocation, leading the agent to enter a negotiation workflow or prepare outbound actions in contexts where the user did not explicitly intend to use this external service.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/api-reference.md:10