video

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest context from .agents/product-marketing-context.md. Malicious content within this file could potentially manipulate the agent's behavior during the video production workflow. Ingestion points: .agents/product-marketing-context.md (SKILL.md). Boundary markers: Not present. Capability inventory: Execution of npm and npx commands for setup (SKILL.md). Sanitization: No content validation or sanitization process is described.
  • [COMMAND_EXECUTION]: The documentation includes shell commands for installing dependencies and bootstrapping projects using npm and npx.
  • [EXTERNAL_DOWNLOADS]: The skill recommends downloading well-known third-party packages such as hyperframes from public registries to enable programmatic video features.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 04:39 PM