web-design-guidelines

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly instructs the agent to fetch live guidelines from the public URL https://raw.githubusercontent.com/Prisma-Labs-Dev/frontend-skills/main/skills/web-design-guidelines/references/web-interface-guidelines.md and to apply rules and output-formatting from that fetched content, so untrusted changes at that third-party source could alter the agent's actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly fetches and uses at runtime the remote guidelines file https://raw.githubusercontent.com/Prisma-Labs-Dev/frontend-skills/main/skills/web-design-guidelines/references/web-interface-guidelines.md, and that fetched content directly supplies the rules and output-format instructions that control the agent's behavior.