aios-long-running-harness
Warn
Audited by Snyk on Apr 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The harness workflow explicitly requires verifying step completion from page evidence and the repository-level guidance references using browser MCP calls and page.extract_text / page.get_html to capture page/html evidence, which implies the agent will fetch and interpret web page content (potentially open, third-party pages) as part of runtime decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata