ClawHub
Back to skill

Security audit

Eureka Feedback

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill transparently helps an agent message a named Eureka bot, but users should verify the Telegram destination before sharing sensitive context.

Install only if you intend to use this Eureka/Telegram workflow. Before using it, verify that `clawdbot`, `@Eureka_Agent_Bot`, the `mason` reply account, and the numeric reply target are yours or trusted; avoid sending secrets, credentials, private project data, or personal information unless that destination is correct.

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 (3)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrase "ask eureka" is broad natural language that could easily appear in ordinary conversation, making unintended invocation plausible. In this skill, accidental activation is more concerning because invocation can cause the agent to send user-provided content to an external Telegram-connected agent, creating risk of unintended delegation or data disclosure.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The phrase "check with eureka" is ambiguous and likely to occur in normal planning or discussion, so it may activate the skill when the user did not intend to delegate externally. Because the skill's core action is to relay messages to another agent over Telegram tooling, accidental triggering could leak context or perform unintended cross-agent communication.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
88% confidence
Finding
The trigger "ask eureka" shadows the common built-in verb "ask," which can create routing ambiguity between normal assistant behavior and this skill. In context, that ambiguity is meaningful because the skill escalates from ordinary conversation to invoking an external agent command, increasing the chance of unintended command execution or message forwarding.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.