skills/akillness/jeo-skills/ax/Gen Agent Trust Hub

ax

Fail

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill frequently instructs the user and agent to install the 'ax' tool by running curl -fsSL https://ax.yusuke.run/install | sh, which executes a remote script without verification.
  • [EXTERNAL_DOWNLOADS]: The setup.sh script downloads platform-specific binaries from https://ax.yusuke.run/download/ and makes them executable on the local system.
  • [COMMAND_EXECUTION]: The skill uses subprocess.run and child_process.exec to interact with the system shell to execute the ax tool.
  • [PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection due to its core function of fetching and processing untrusted web data.
  • Ingestion points: Untrusted web content fetched via ax <url> (SKILL.md).
  • Boundary markers: Use of --outline for structure discovery and --budget for token capping (SKILL.md).
  • Capability inventory: Shell command execution capabilities via the ax CLI wrappers (tools/ax_tool.py, tools/ax-tool.js).
  • Sanitization: No explicit sanitization of the fetched web data is performed before it is presented to the agent.
Recommendations
  • HIGH: Downloads and executes remote code from: https://ax.yusuke.run/install - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 27, 2026, 11:38 AM
Security Audit — agent-trust-hub — ax