x-hashtag-research
Warn
Audited by Snyk on Jun 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). Workflow step 2/4/5 ingests outsider-authored free text from X live search (public posts’ status URL,本文, card title/domain, and images’ associated text) into the agent’s LLM context for classification and deep-dive.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata