ce-sweep

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

• Third-party content exposure detected (medium risk: 0.30). The workflow continuously monitors and reads externally-authored GitHub issues, Slack messages, and inbound emails via connectors (references/sources/github-issues.md, slack.md, email.md) without the agent first selecting a specific item.

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

• Potentially malicious external URL detected (medium risk: 0.30). The analysis script references the external OpenAI API endpoint (https://api.openai.com/v1/audio/transcriptions) for media transcription, which constitutes an unverifiable runtime external dependency under strong/official external API classification.