text-to-video

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill is configured to access sensitive authentication files. Evidence: Frontmatter requirements and metadata specify reading credentials from ~/.meitu/credentials.json to obtain MEITU_OPENAPI_ACCESS_KEY and MEITU_OPENAPI_SECRET_KEY for the Meitu API.
  • [COMMAND_EXECUTION]: Executes a third-party CLI tool with runtime parameters derived from user input. Evidence: The skill invokes the meitu command (e.g., meitu text-to-video --prompt "{video_description}" ...) to process video generation tasks.
  • [PROMPT_INJECTION]: Identified vulnerability surface for indirect prompt injection through untrusted data ingestion.
  • Ingestion points: User-provided content for the prompt and video_description parameters used in the meitu command.
  • Boundary markers: None identified; user input is interpolated directly into command-line arguments.
  • Capability inventory: Execution of the meitu CLI tool and file writing permissions to local directories (./output/, ~/.openclaw/workspace/visual/).
  • Sanitization: There is no evidence of validation or sanitization of the user-provided prompt strings before they are passed to the execution tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 06:03 AM
Security Audit — agent-trust-hub — text-to-video