ai-gateway
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
@vesely/ai-gateway-clipackage from the NPM registry to provide its core functionality. This package is an official resource provided by the skill author. - [COMMAND_EXECUTION]: The skill relies on shell commands to check for the CLI's presence (
which), install it globally if missing (npm install -g), and execute generation tasks. - [INDIRECT_PROMPT_INJECTION]: The skill accepts arbitrary text prompts and file content as input to be processed by external AI models, which is an inherent part of its content generation functionality.
- Ingestion points: User-provided prompts and piped file content in commands like
cat file.md | ai-gateway "<prompt>". - Boundary markers: None explicitly defined; the skill passes raw input to the CLI tool.
- Capability inventory: Shell command execution and network communication via the external CLI tool.
- Sanitization: No specific sanitization or filtering of input text is implemented in the skill instructions.
Audit Metadata