magic-hour-explainer-video
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied source documents or briefs to generate video scripts and media. This creates an attack surface where malicious instructions embedded in the source material could potentially influence the agent's behavior during the script-writing or tool-invocation phases.
- Ingestion points: The skill instructions explicitly direct the agent to "Read the actual source material" to determine the script content (SKILL.md).
- Boundary markers: There are no specific instructions or delimiters provided to help the agent distinguish between informational content and potential embedded commands within the source material.
- Capability inventory: The skill utilizes a suite of media generation tools including
ai_voice_generator_create_audio,ai_voice_cloner_create_audio,ai_image_generator,ai_image_editor, andimage_to_video_create_videovia the Magic Hour MCP. - Sanitization: The instructions do not specify any sanitization or validation steps for the input source material beyond factual traceability recommendations.
Audit Metadata