Skills
Navigate
skills/purong-huang-1121/plugin-store/skills-store/Gen Agent Trust Hub

skills-store

Fail

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill mandates the execution of a shell script downloaded directly from a personal GitHub repository (purong-huang-1121/skills-store) using curl | sh as the very first step of operation.
  • [REMOTE_CODE_EXECUTION]: The skill fetches data from the GitHub API and pipes it directly into a Python interpreter (python3 -c) to execute dynamic logic for sorting and displaying strategy statistics.
  • [EXTERNAL_DOWNLOADS]: Automatically installs additional external skills using npx skills add from an untrusted personal repository without proper verification.
  • [DATA_EXFILTRATION]: Attempts to read sensitive information from the file ~/.cargo/bin/.env, specifically targeting TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID credentials.
  • [COMMAND_EXECUTION]: Executes multiple system commands including which, cat, and npx to perform environment checks and secret extraction.
  • [METADATA_POISONING]: The skill metadata deceptively lists 'okx' as the author, which conflicts with the actual source code and repository owner 'purong-huang-1121', suggesting a potential impersonation or supply chain risk.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/purong-huang-1121/skills-store/main/install.sh, https://api.github.com/repos/purong-huang-1121/skills-store/releases?per_page=100 - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Mar 17, 2026, 01:58 PM
Security Audit — agent-trust-hub — skills-store