ai-content-pipeline

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). These URLs are potentially suspicious because the skill instructs piping a remote installer (curl https://cli.inference.sh | sh) and running a third‑party CLI from an unverified domain (inference.sh), which is a high‑risk distribution vector for malware even though the docs/blog pages and the PNG are low‑risk content — additionally the placeholder audio URL (https://your-music.mp3) is untrusted and could hide malicious payloads.

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly includes a "Research" step and Pipeline Pattern 3 using "Tavily Search" (tavily/search-assistant) to gather information from the open web which is then summarized by an LLM and used to drive downstream generation, so the agent ingests untrusted third-party web content that can influence 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 running a remote install script with "curl -fsSL https://cli.inference.sh | sh", which fetches and executes remote code at runtime and is required to use the infsh commands, so https://cli.inference.sh is flagged.