image-generate

Pass

Audited by Gen Agent Trust Hub on Oct 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx agent-media@latest to download and run code from the npm registry.
  • [COMMAND_EXECUTION]: The skill performs image generation by executing shell commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill incorporates untrusted user prompts into a shell command.
  • Ingestion points: The --prompt parameter in SKILL.md.
  • Boundary markers: Absent; the prompt is passed directly as a command-line argument.
  • Capability inventory: Execution of commands through the shell environment.
  • Sanitization: No sanitization or escaping mechanisms are described for the input prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 19, 2026, 06:30 PM