hermoso-generate
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and execute the
hermosoCLI tool from the npm registry usingnpx -y hermoso. This package is associated with the skill's vendor (hermoso-ai). - [COMMAND_EXECUTION]: Shell commands are used to interact with the Hermoso platform for authentication (
hermoso auth login), capability discovery (hermoso capabilities), and media generation (hermoso generate). It also includes the ability to call arbitrary vendor tools viahermoso call. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data as reference inputs for ad generation.
- Ingestion points: Local file paths and remote URLs provided via the
--refand--imagearguments inSKILL.md. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands are defined for the input data.
- Capability inventory: The skill has the capability to execute shell commands through the Hermoso CLI and fetch remote assets.
- Sanitization: No explicit sanitization or validation of the input files or URL content is performed before processing.
Audit Metadata