live-session-to-on-demand-modules
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes transcription data from external recordings which could potentially contain malicious instructions. \n- Ingestion points: Transcribed audio from user-provided source videos (SKILL.md, Step 2). \n- Boundary markers: The workflow includes a manual confirmation step where the agent proposes a module list to the user before performing any edits (SKILL.md, Step 3). \n- Capability inventory: The skill uses the
clueso-mcptool to perform video editing, split clips, and create new projects (SKILL.md, Workflow). \n- Sanitization: No explicit sanitization or filtering is mentioned for the transcription content before analysis.
Audit Metadata