PPT Generator Pro with Driving Effect

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands to facilitate PPT generation and financial operations.
  • Uses curl to interact with external image and video generation APIs via proxy-monetize.fluxapay.xyz.
  • Utilizes the fluxa-wallet CLI tool for managing API payments and on-chain transactions.
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends the installation of external dependencies.
  • Directs the user to install @fluxa-pay/fluxa-wallet globally via npm to enable the payment features.
  • Fetches API metadata and endpoint discovery information from vendor-managed servers.
  • [DATA_EXFILTRATION]: The skill transmits user-provided content and generated prompts to external processing services.
  • Transmits document content and image generation prompts to the Nano Banana and Kling AI APIs hosted at proxy-monetize.fluxapay.xyz.
  • These operations are documented as the primary function of the skill and utilize vendor-owned infrastructure.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its document analysis phase (Category 8).
  • Ingestion points: Document content provided by the user (or generated) is read from the local environment and processed to create slides_plan.json.
  • Boundary markers: The prompt templates do not currently implement specific boundary markers or 'ignore embedded instructions' directives when interpolating user content.
  • Capability inventory: The skill has the ability to execute network requests, write files to the local disk, and perform financial transactions via the wallet CLI.
  • Sanitization: No explicit sanitization or filtering of user-provided document content is performed before it is included in the LLM prompts for image/video generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 02:38 AM