ClawHub

agnes-图片生成

Security checks across malware telemetry and agentic risk

Overview

This image-generation skill does what it says, but it handles API keys and third-party uploads in ways users should review carefully.

Install only if you are comfortable sending prompts and any edited images to Agnes AI. Prefer setting AGNES_API_KEY as an environment variable, avoid pasting real API keys into chat, and do not rely on any shared built-in key for private or accountable work.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
98% confidence
Finding
The skill explicitly states that it contains a built-in default Agnes API key and encourages using it as a fallback. Embedding service credentials in a distributable skill creates shared-secret exposure risk, unauthorized billing/abuse, and makes it impossible to enforce per-user accountability or least privilege.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill sends prompts and potentially user-supplied images to an external HTTP API but does not clearly warn users about third-party data transfer, retention, or privacy implications. For image-editing requests, this may expose sensitive images, embedded metadata, or confidential prompt content to an external provider without informed consent.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The documentation instructs users to provide API keys directly in chat ('Key 是 sk-xxx'), which can leak secrets into conversation history, logs, analytics, screenshots, or downstream tooling. Encouraging plaintext credential sharing materially increases the chance of credential compromise and subsequent unauthorized API use.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal