hermoso-product-photoshoot

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions involve running npx -y hermoso, which downloads and executes a package from the NPM registry. This package is a vendor resource provided by the skill author to enable image generation and management.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data by passing user-supplied image references and scene descriptions into CLI commands.
  • Ingestion points: User-provided image paths, URLs, and descriptive prompts are used as arguments for the hermoso generate command in SKILL.md.
  • Boundary markers: The skill does not explicitly define sanitization or boundary markers (such as specific delimiters) to separate user content from the CLI command structure.
  • Capability inventory: The skill requires the Bash tool to execute commands and interact with the filesystem and network via the Hermoso CLI.
  • Sanitization: No explicit input validation, escaping, or filtering is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 06:22 AM