Axiom Distributed Science

• Outcome: Pass
• Latest audit: May 29, 2026, 8:16 PM
• Version:
  1.1.0

Overview

This is an instruction-only skill for querying a public science API, with a clearly documented optional submission endpoint.

Install this only if you want an agent to query Axiom's public science APIs. Before using the suggestion endpoint, confirm that the experiment idea and author name are safe to send to axiom.heliex.net, and do not include secrets, private research details, or personal data.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The skill advertises very broad invocation conditions such as general scientific research, distributed computing, and curiosity about AI-driven research platforms. That can cause the agent to activate this skill for loosely related prompts and send user queries to an external service without a narrowly scoped user intent, increasing the chance of unnecessary data disclosure or unexpected tool use.

VirusTotal

64/64 vendors flagged this skill as clean.