og-image-design

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). The prompt instructs piping and running a shell script from an unverified domain (cli.inference.sh/inference.sh), which is a high-risk pattern for arbitrary code/malware distribution; the yoursite.com URLs are just placeholder image/page links and not themselves dangerous.

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

• Third-party content exposure detected (high risk: 0.70). SKILL.md's "Testing OG Images" section explicitly runs a web search tool (infsh app run tavily/search-assistant) and lists external debugger sites (developers.facebook.com, cards-dev.twitter.com, linkedin.com/post-inspector, opengraph.xyz), which indicates the agent will fetch and interpret untrusted third-party web content that could influence its actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The Quick Start includes a runtime fetch-and-execute command (curl -fsSL https://cli.inference.sh | sh) which downloads and runs remote code and the skill's examples explicitly depend on the inference.sh CLI, so https://cli.inference.sh is a runtime external dependency that executes code.