feature-video

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of human-readable instructions for producing software demo videos. It does not contain any executable code, scripts, or network operations.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill demonstrates security best practices by explicitly instructing the agent to protect sensitive information: "Never expose private accounts, keys, messages, or customer data in footage."
  • [INDIRECT_PROMPT_INJECTION]: While the skill involves inspecting a working application (an external source of data), the instructions are focused on visual recording and editing rather than parsing and executing commands from that UI. The surface for malicious instruction ingestion is minimal in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 05:30 AM