ClawHub

AgentWyre

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a legitimate AgentWyre integration for fetching AI ecosystem intelligence, with expected but privacy-relevant API-key and network use.

Install only if you intend to use AgentWyre as an external intelligence provider. Configure a dedicated, revocable AGENTWYRE_API_KEY, avoid sending sensitive internal context in AI-news queries, and be aware that broad AI update prompts may cause the skill to contact agentwyre.ai.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 demonstrates access to environment variables and outbound network calls, but does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: an agent or platform may invoke the skill without realizing it can read secrets like AGENTWYRE_API_KEY and contact external services. In a skill ecosystem, undeclared capabilities increase the chance of unintended data exposure or bypass of least-privilege controls.

Vague Triggers

Medium
Confidence
74% confidence
Finding
The trigger language is very broad, covering generic requests like 'what's new in AI' or 'AI news,' which can cause this skill to activate in many ordinary conversations. Over-broad routing increases attack surface by unnecessarily invoking a networked skill, potentially leaking user context to an external service or overshadowing more appropriate local answers. The risk is amplified because the skill is designed to fetch fresh external intelligence, not just static reference content.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal