@1892/design-md

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

• Third-party content exposure detected (high risk: 0.80). Yes — the SKILL.md explicitly instructs the agent to download and read DESIGN.md files from the public awesome-design-md GitHub repo (see Quickstart step 2 and the catalog links), so untrusted, user-contributed third-party markdown is ingested and used to drive agent decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs downloading DESIGN.md files at runtime from https://github.com/VoltAgent/awesome-design-md/tree/main/design-md/{site}/ and then passing that fetched markdown to coding agents to direct UI generation, so external content would directly control agent prompts.