autoresearch-fleet
Warn
Audited by Snyk on May 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The orchestrator (orchestrator.sh) explicitly enables web search/fetch tools (PI_TOOLS, codex_extra web_search flag, and a claude --tools injection) and, in plateau mode, instructs the agent to "Use WebSearch" and implement changes based on what it finds, so the agent will fetch and read untrusted public web content that can directly influence its coding and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata