runbookhermes-aiops-agent

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

• Third-party content exposure detected (medium risk: 0.30). The workflow accepts incidents and alerts via webhooks and API endpoints (such as Alertmanager and HTTP inputs), allowing outsider-authored text payloads to be ingested.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references cloning a repository from GitHub (https://github.com/Tommy-yw/RunbookHermes.git), which constitutes an operational dependency retrieved from a common unofficial source.