botlearn-healthcheck

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (data_collect.md + check_skills.md) and its collection scripts (notably scripts/collect-skills.sh and instructions that run "clawhub search botlearn") explicitly query the public clawhub/registry to ingest available skill listings into DATA.skills, and those results are used to generate install recommendations and drive follow-up actions (e.g., install commands), so untrusted, third‑party registry content can materially influence decisions and tool use.