opentrade-token

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.95). Suspicious — the skill instructs curl | sh on a raw .sh hosted in a relatively unknown GitHub repo (6551Team/openskills) and references a custom domain (6551.io) for API tokens, which together are high-risk patterns because they allow remote arbitrary code execution and credential harvesting from an untrusted/low‑reputation source.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This skill's required workflow (SKILL.md) runs opentrade CLI commands (e.g., token search, toplist, price-info, holders) that fetch public token metadata and lists (including websiteUrl, twitterUrl, telegramUrl, explorerUrl) from open/public APIs and also instructs installing code via curl from raw.githubusercontent.com, and those untrusted, user-generated/public sources are read and used to make follow-on decisions (liquidity checks, communityRecognized, and whether to proceed to swaps), creating a clear path for indirect prompt injection.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.95). The skill instructs at runtime to run a remote install script via curl -sSL https://raw.githubusercontent.com/6551Team/openskills/main/skills/opentrade/install.sh | sh which fetches and directly executes remote code and is used as a required dependency.