kling-video

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @runapi.ai/kling package from the NPM registry to interact with the Kling AI API.
  • [COMMAND_EXECUTION]: Documentation includes a standard installation command (npm install @runapi.ai/kling) intended for the developer's environment setup.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data via video generation prompts (e.g., in client.textToVideo.run).
  • Ingestion points: User-provided strings passed to the prompt and multi_prompt parameters in SKILL.md.
  • Boundary markers: None provided in the instruction templates.
  • Capability inventory: The skill uses a scoped SDK to make network requests to the RunAPI backend; it does not perform direct file system writes or shell command execution with user input.
  • Sanitization: No explicit sanitization or validation of the prompt content is described within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 06:58 AM
Security Audit — agent-trust-hub — kling-video