app-sizzle

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a transparent multi-stage workflow, starting with asset sourcing and analysis before any video generation. This design ensures that the agent's actions are grounded in the user's requested app identity.
  • [EXTERNAL_DOWNLOADS]: The skill fetches application screenshots and metadata from the Apple App Store using mcp__pika__fetch_appstore_screens and captures website visuals via mcp__pika__capture_website. These are well-defined, legitimate operations necessary for the skill's primary function of generating app promos.
  • [SAFE]: Video generation is managed through mcp__pika__generate_reference_video using specific providers (Seedance and Kling). The skill includes detailed error-handling and recovery logic for provider-side issues such as timeouts or moderation false positives, ensuring reliable operation without bypassing security protocols.
  • [COMMAND_EXECUTION]: The skill does not perform any direct shell command execution or privilege escalation. All operations are conducted through the designated MCP (Model Context Protocol) toolset provided by the platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:43 PM
Security Audit — agent-trust-hub — app-sizzle