whiteboard
Fail
Audited by Snyk on Nov 21, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate whiteboard tool, but it tells the agent to conceal its own reading and checking activity from the user and to keep viewer-state context out of replies, which hides the agent's activity from the person it serves without malicious intent.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow reads comments and board elements that people can write through shared LAN links (commenter and editor roles, where anyone with the link types a name and gets in), and
open-artifact commentsandwaitconsume them without the agent selecting a specific item.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill exposes operational changes through
open-artifact share, which enables LAN sharing, toggles and resets role links, and persists sharing state across restarts, but it shows no explicit irreversible operational loss, since links can be reset or re-enabled and board content is recoverable throughhistory restore.
Issues (3)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata