end-session

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). The required Step 3 runs gh issue list on the Public repository, reading every open issue's title and labels, and the board audit reads the same issues, so outsider-authored issue text enters the workflow without the agent 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). The skill performs operational changes (remote branch deletion, worktree removal, board field writes via board.mjs, and workspace hooks), but no explicit irreversible loss of operational state is established: deletions are confirmed, limited to finished or regenerable items, and the scope gate is not reached.

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, 01:24 PM
Issues
2