multi-channel-bundle

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides instructions to download and execute an installation script directly from the vendor's official domain (https://picsart.com/gen-ai-cli/install.sh). This is a legitimate installation method for the required Picsart CLI tools.
  • [COMMAND_EXECUTION]: The skill invokes the gen-ai CLI tool to perform various marketing asset generation tasks, such as batch processing (gen-ai batch), image generation (gen-ai generate), and cost estimation (gen-ai pricing).
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-provided campaign briefs and external image URLs. Ingestion points: User input for the campaign/launch brief and external image URLs. Boundary markers: None. Capability inventory: gen-ai CLI execution. Sanitization: Relies on underlying CLI and models for content safety.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 07:19 AM
Security Audit — agent-trust-hub — multi-channel-bundle