ai-rag-pipeline

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). Most links are documentation and media on a third‑party domain (inference.sh) and example.com placeholders, but the skill explicitly instructs running curl -fsSL https://cli.inference.sh | sh — a direct remote-execution of an unverified shell script from a non‑well‑known domain, which is a high‑risk distribution pattern that could deliver malware.

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly runs web searches and extracts content from external URLs (e.g., the "URL Content Analysis" example using tavily/extract on arbitrary URLs and multiple examples using tavily/search-assistant and exa/search) and then injects those untrusted results into LLM prompts, allowing third-party content to directly influence agent outputs and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The Quick Start instructs users to run "curl -fsSL https://cli.inference.sh | sh", which fetches and executes remote code from https://cli.inference.sh as a required dependency for the infsh CLI, so the URL directly executes remote code at runtime.