Skills
skills/starchild-ai-agent/community-skills/okx-dex-token/Gen Agent Trust Hub

okx-dex-token

Fail

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill downloads and executes an installer script (install.sh or install.ps1) from https://raw.githubusercontent.com/okx/onchainos-skills/. This pattern allows for the execution of arbitrary code from a remote source on the user's machine.
  • [EXTERNAL_DOWNLOADS]: The skill fetches several external resources, including the installer script, binary checksums (installer-checksums.txt), and the application binary itself from GitHub releases.
  • [COMMAND_EXECUTION]: The skill heavily relies on shell command execution, using curl, sh, and PowerShell to manage tool installation, versioning, and integrity checks.
  • [METADATA_POISONING]: The YAML frontmatter in SKILL.md identifies the author as 'okx', which contradicts the identified author 'Starchild-ai-agent'. This discrepancy can mislead users regarding the origin and safety of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted token data (names, symbols, and tags) from on-chain sources via the CLI tool.
  • Ingestion points: Data returned from onchainos token search and token advanced-info (e.g., tokenTags).
  • Boundary markers: None are defined in the instructions to separate untrusted data from agent instructions.
  • Capability inventory: The skill utilizes shell execution and network access across its primary logic.
  • Sanitization: No sanitization or escaping mechanisms are prescribed for the retrieved data.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/okx/onchainos-skills/${LATEST_TAG}/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 23, 2026, 01:20 PM