edit-dialogue
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data via media URLs and video transcriptions.
- Ingestion points: Media URLs from social platforms and local file uploads are processed into transcriptions as described in
references/media-input.mdandSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the processed transcript data.
- Capability inventory: Includes tools for project management and media synthesis (
projects_create,create-dialogue-video). - Sanitization: No specific sanitization methods are mentioned for transcript content.
- [COMMAND_EXECUTION]: The documentation provides example
curlcommands for uploading media files to the sync. labs infrastructure. - [EXTERNAL_DOWNLOADS]: The skill references installation of official Synchronicity Labs packages (
syncsdk,@sync.so/sdk) and an MCP server.
Audit Metadata