p-video-2-pro
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for generating video clips using the Pruna AI platform. It utilizes official vendor endpoints (api.pruna.ai) for file uploads and prediction requests.
- [EXTERNAL_DOWNLOADS]: The skill references other related skills from the same vendor's repository (PrunaAI/pruna-skills) via standard installation commands. These are legitimate dependencies for the skill's extended functionality.
- [COMMAND_EXECUTION]: The skill provides example curl commands for interacting with its API. These commands use an environment variable placeholder ($PRUNA_API_KEY) for authentication, which is a secure and standard practice for managing credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate video. Ingestion points: User prompt input (SKILL.md); Boundary markers: 'Fidelity check' and 'Agent habit' instructions require the agent to lock user facts and validate prompts; Capability inventory: HTTP POST calls to api.pruna.ai; Sanitization: Relying on agent behavioral constraints and vendor-side API safety.
Audit Metadata