sjinn-video-generation

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates untrusted data from user prompts and external media URLs into its execution flow.
  • Ingestion points: User-provided text for the --prompt argument and external URLs provided via --image, --media-urls, and other media options in SKILL.md and references/models.md.
  • Boundary markers: There are no markers or instructions defined to prevent the agent from following malicious commands embedded within the user prompt or the metadata of external media.
  • Capability inventory: The skill executes shell commands via the sjinn CLI, which can interact with the file system and perform network uploads.
  • Sanitization: The instructions do not include steps to sanitize or validate user input before it is passed to the shell commands.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands using the sjinn CLI to perform video generation and authentication tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:27 PM
Security Audit — agent-trust-hub — sjinn-video-generation