skill-discovery

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

• Third-party content exposure detected (high risk: 0.75). At runtime the workflow runs npx skills find [topic] and npx skills add owner/repo@skill --yes, which fetches and installs outsider-authored skill packages from the public open skills ecosystem (e.g., skills.sh/GitHub repos), and the installed skill’s README/code/docs are typically ingested as free text during install/assessment and/or later execution.