jarvis-starter

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly performs GitHub discovery and registry searches as part of its required bootstrap/adopt workflow (see "Phase 2 — Proposal (stack + skills from registry + GitHub discovery via on-demand/skill-discovery/)" and multiple references to "jarvis find" / "sweep GitHub" in SKILL.md and archive files), meaning the agent fetches and interprets public, user-generated GitHub content which can directly affect recommendations and install/action decisions.