pollo-ai-video-generator
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements strong credential security by storing API keys in a local config file (~/.pollo/config.toml) and instructing the agent to never include the key in bash commands to avoid exposure in process lists or shell history.
- [EXTERNAL_DOWNLOADS]: Network operations are restricted to the vendor's official domain (pollo.ai) for API requests and media uploads.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text prompts for video generation. While this is an ingestion surface for external data, it is handled within structured API requests to a specific video model, presenting low risk to the local environment.
- [COMMAND_EXECUTION]: The skill executes bundled Python scripts for task polling and API interaction, utilizing standard library components without dangerous dynamic execution patterns.
Audit Metadata