forge-debugger

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and read external, user-generated Atlassian logs and site data (e.g., "forge logs -e production --site " and the Step 6 logs reading instructions in SKILL.md), which the agent must interpret to decide and execute fixes, exposing it to untrusted third-party content.