use-findskill

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

• Third-party content exposure detected (high risk: 0.90). This skill instructs the agent to discover and install skills from the public findskill.md registry (e.g., npx findskill install <skill>) and to read the installed SKILL.md files under ~/.claude/skills//SKILL.md, which are untrusted, user-contributed third-party content the agent is explicitly expected to ingest and act on.