scenario-video-assembly

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection where malicious instructions could be embedded in the metadata of assets processed by the skill.
  • Ingestion points: The skill reads properties (such as duration and frameRate) from external assets via asset_get in SKILL.md.
  • Boundary markers: The instructions lack delimiters or "ignore embedded instructions" warnings when processing these properties.
  • Capability inventory: The skill coordinates complex operations using model_run, asset_download, and upload_asset throughout SKILL.md.
  • Sanitization: There is no logic provided to sanitize or validate these external inputs before they influence the logic of the video assembly process.
  • [EXTERNAL_DOWNLOADS]: The instructions recommend installing additional skills from the scenario-labs repository using the platform's skill management utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 07:46 AM
Security Audit — agent-trust-hub — scenario-video-assembly