yao-doubao-crawler

Warn

Audited by Snyk on Jul 26, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). SKILL.md’s required workflow runs the web/mobile crawler, which records Doubao-displayed answer text and visible reference titles/URLs (outsider-authored content from Doubao and referenced sources) into crawl JSON, and Stage 2 (scripts/analyze_doubao_results.py) then feeds that text into the agent’s LLM context via whatever downstream report/analysis generation uses LLM—so the runtime context can include non-user-authored free text from those answers/references.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 26, 2026, 04:12 AM
Issues
1
Security Audit — snyk — yao-doubao-crawler