writing-style

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly allows fetching and analyzing content from a "Repository | GitHub URL | Fetch and analyze", which is a public, user-generated source that the agent will read and use to determine style characteristics that drive subsequent tool calls and actions (outline phase), creating a clear vector for indirect prompt injection.