tailwindcss

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to "fetch and read the live documentation" from Tailwind's public docs (https://tailwindcss.com/docs), meaning the agent will ingest and act on untrusted third-party web content that can influence its code-writing and decisions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent to "MUST fetch and read the live documentation" at runtime, meaning external content from https://tailwindcss.com/docs would be fetched and used to directly control the agent's instructions and outputs.