sanity-pkg-utils

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill describes the installation of the @sanity/pkg-utils package via pnpm. This package is maintained by a trusted organization.
  • [COMMAND_EXECUTION]: The skill provides instructions for executing build and validation commands such as pkg build, pkg watch, and pkg check. These are standard development operations for the intended tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by reading and interpreting configuration files like package.json and package.config.ts. While this constitutes an ingestion surface for potentially untrusted data that could influence the agent's tool-using behavior, there are no malicious patterns detected in the skill's implementation.
  • Ingestion points: Reads metadata and build instructions from package.json and package.config.ts.
  • Boundary markers: None explicitly defined in the documentation.
  • Capability inventory: Executes shell commands (pkg) and reads configurations in the project directory.
  • Sanitization: Standard CLI argument parsing is assumed for the underlying tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 10:54 AM
Security Audit — agent-trust-hub — sanity-pkg-utils