agent-tools

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). They point to a single third‑party domain that hosts a piped installer (curl | sh) and downloadable CLI binaries (dist.inference.sh/manifest), which is a high‑risk distribution pattern because executing remote scripts or binaries from an unfamiliar domain can deliver malware—though the presence of checksums and Sigstore verification are useful mitigations.

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md and references explicitly include web-search apps (e.g., infsh app run tavily/search-assistant and Exa Search listed in SKILL.md and references) which fetch and return open/public web content that the agent would read and could influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly tells users to run a remote installer with "curl -fsSL https://cli.inference.sh | sh" (which downloads binaries from https://dist.inference.sh), so remote code is fetched and executed as a required dependency.