zener-language

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

• Third-party content exposure detected (high risk: 0.90). This skill's workflow explicitly tells the agent to run "pcb doc" and read package source files (including cross-package Module() and pinned URL packages such as "github.com/org/repo/path@v0.2.5") and to read actual .zen sources, which requires fetching and interpreting content from arbitrary public package URLs and registries.