skills/mountain-loop/yaak/use-yaak/Gen Agent Trust Hub

use-yaak

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill contains instructions to install the official @yaakapp/cli package from the NPM registry if the command is not available in the environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection due to its core functionality of ingesting external data specifications.
  • Ingestion points: The skill uses yaak import to process external files in formats such as OpenAPI, Postman, Insomnia, and Bruno collections, which could contain malicious instructions.
  • Boundary markers: There are no explicit boundary markers or instructions to ignore embedded prompts within the imported data.
  • Capability inventory: The skill is authorized to use the yaak CLI, npm, npx, and standard bash utilities.
  • Sanitization: The instructions do not describe any sanitization or validation steps for the content of imported files prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 08:50 AM