skill-finder-cn

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

• Third-party content exposure detected (high risk: 0.70). This skill explicitly searches the public ClawHub registry (SKILL.md workflow step "搜索 ClawHub", scripts/search.sh calling clawhub search, and .clawhub/origin.json registry "https://clawhub.ai"), so it ingests untrusted third-party skill listings/descriptions that the agent reads and uses to recommend or install skills.