openclaw-research-paper-push-skill

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

• Third-party content exposure detected (high risk: 0.85). At runtime the skill queries the public OpenAlex API for newly published papers and then ingests the returned paper metadata (e.g., titles/authors/venues/abstract-derived fields) into the agent’s generated Chinese digest, which is outsider-authored free text from a public web data source.