post-incident-review

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads internal records, incident tickets, and chat channel exports specified in the inputs, which can contain external user-submitted content from incident reports or communication channels.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill references an external MCP server and setup URL for ISMS Copilot (ismscopilot.com) which constitutes an unverifiable third-party operational dependency.