building-glamorous-tuis

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md) explicitly recommends tools that ingest public, user-controlled content—e.g., Glow usage for "From URL" markdown (references/shell-scripts.md) and Mods for piping arbitrary files/command output to an AI (references/shell-scripts.md and references/mods examples)—so the agent could be asked to read and act on untrusted third‑party web or user-generated content which can materially influence subsequent actions.