creativeclaw-swap-characters
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external media content and user-provided instructions to perform video swaps, creating a potential surface for indirect instructions embedded in data.
- Ingestion points: External media is ingested via
video_url,image_urls, andmedia_fileparameters as described inSKILL.mdandplatform-upload.md. - Boundary markers: The instructions do not define clear delimiters or specific warnings to isolate the content of processed media from the agent's operational logic.
- Capability inventory: The skill utilizes powerful tools for media generation and assembly, including
swap_video_characters,merge_media, andstitch_clips. - Sanitization: No explicit sanitization or validation of external media metadata or content is mentioned in the workflow.
Audit Metadata