knowledge-base
Warn
Audited by Snyk on Nov 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The only outsider-authored free text enters through
importmode, where the agent fetches a user-selected arbitrary web page with the host web tool; the attacker can publish a page but cannot force the agent to fetch it, andask/routing read only the team's own stored packs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata