workflow-onboarding

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text is fetched from the public/other-repo registry dividedby/skills docs/agents/labels.md (and dividedby/skills docs/agents/installed-skills.md) at runtime and then ingested into the agent’s context to generate the install plan and seed docs/agents/installed-skills.md.