sheets
Warn
Audited by Snyk on Nov 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Comments that people write on Sheet cells, including guests with commenter links shared on the LAN, land in
comments.json, and the required workflow reads them viacommentsand monitors them withopen-artifact wait, so an outsider can submit text the agent consumes without selecting an item.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). Standalone
open-artifact shareturns on LAN exposure of the local Sheet server and writes share links and guests, a supporting-environment change, but no irreversible operational loss is established (deletes are restorable and cell overwrites are content edits), so it is low.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata