social-media-video
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill contains standard instructional content for video production and does not exhibit any malicious patterns, credential theft, or unauthorized network activity.
- [NO_CODE]: The skill consists entirely of markdown instructions and procedural logic for the AI agent; no executable scripts or external code dependencies are included.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting external user data to generate creative outputs.
- Ingestion points: User video descriptions, triggers, and project footage references (SKILL.md).
- Boundary markers: None specified in the instructions.
- Capability inventory: Video generation using Seedance 2.5 and audio generation through ElevenLabs MCP or compatible APIs.
- Sanitization: None specified for user-provided strings.
Audit Metadata