slides

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). Guests who join through a shared LAN link with the commenter or editor role can post comments, which are saved to comments.json, and the required Comments workflow has the agent list and act on those open threads via open-artifact comments and wait, so outsider-authored text reaches the agent without it 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 can make persistent operational changes, such as sharing the deck on the local network via open-artifact share, starting a background server, and writing a git pre-commit hook, but no operation shown causes explicit irreversible operational loss (deleting slides, assets or history is content loss or reversible), so gate 2 fails and the tier is low.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 21, 2026, 02:54 AM
Issues
2