shorts-editor

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill communicates with an external API endpoint at https://mega-api-prod.nemovideo.ai/api/v1/generate. This network operation is necessary for the skill's primary function of processing and editing video footage via the NemoVideo service.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it transcribes raw video footage and processes user-supplied edit descriptions.
  • Ingestion points: Transcription of long-form audio/video content (e.g., in the 'Repurpose Long-Form' use case) which could contain embedded instructions.
  • Boundary markers: None identified in the provided prompt templates to separate transcribed content from system instructions.
  • Capability inventory: The skill utilizes network access (curl) and local configuration file access (~/.config/nemovideo/).
  • Sanitization: No specific sanitization or filtering of transcribed text is described before it is used for insight extraction.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:31 PM
Security Audit — agent-trust-hub — shorts-editor