fusion-issue-task-planning

Warn

Audited by Snyk on Mar 6, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly requires a target issue reference (owner/repo#number or URL) and its workflow (see SKILL.md step 2 "Research the user story") states it will gather and interpret the issue title, body, acceptance criteria, ancestor chain and related links from GitHub issues — user-generated, potentially public content that can materially change planning and delegated publish/repair actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 12:51 AM