skills/vesely/skills/ai-gateway/Gen Agent Trust Hub

ai-gateway

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @vesely/ai-gateway-cli package from the NPM registry. This package is provided by the same author as the skill ('Vesely') and is a legitimate vendor resource.- [COMMAND_EXECUTION]: The skill executes the ai-gateway CLI to perform content generation. This is the primary intended function of the skill.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it supports piping external file content directly into the generator tool (e.g., cat file.md | ai-gateway ...).
  • Ingestion points: External file content via stdin (mentioned in SKILL.md).
  • Boundary markers: None provided in instructions or command templates.
  • Capability inventory: Executes generation commands; no file-write or network-send capabilities beyond those of the specific generation tool.
  • Sanitization: No sanitization of the piped input is performed by the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 07:15 PM
Security Audit — agent-trust-hub — ai-gateway