saas-security-posture

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

• Third-party content exposure detected (medium risk: 0.30). The workflow queries GitHub APIs and reads repository settings and installations, which can contain outsider-authored content via third-party GitHub apps and issues/PR metadata.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.90). The skill prompt instructs the agent to create system scripts in /usr/local/bin/ and modify system cron configurations in /etc/cron.d/, which requires root/sudo privileges and modifies system state.