Transcription Automation
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Potential surface for indirect prompt injection through untrusted media inputs.
- Ingestion points: Transcribes untrusted audio and video content from Zoom, YouTube, and RSS feeds as defined in the integration workflows (SKILL.md).
- Boundary markers: Lacks delimiters or instructions to the model to ignore potential commands spoken within the transcribed media content.
- Capability inventory: The skill has the capability to distribute processed transcripts and summaries to external services including Notion, Slack, and email (SKILL.md).
- Sanitization: The skill does not perform sanitization or filtering of transcribed text for adversarial instructions before it is processed by the summarization model.
Audit Metadata