web-research
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The workflow delegates to research subagents that use the
web_searchtool and then save findings containing “source URLs” and “relevant quotes” into localresearch_[topic_name]/findings_[subtopic].md, which are later read viaread_fileand thus feed outsider-authored web page text into the agent’s LLM context during synthesis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata