pest-testing

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill's operations are restricted to scanning local project files and generating test code based on established Laravel and Pest PHP patterns.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it reads and processes application source code to generate output. Ingestion points: The skill scans models, controllers, services, and routes within the Laravel project. Boundary markers: No specific delimiters or instructions are provided to the agent to disregard malicious content embedded within the source files. Capability inventory: The skill is designed to create and modify files on the filesystem, specifically test suites and factories. Sanitization: No automated sanitization or verification of the input source code is specified.
  • [COMMAND_EXECUTION]: The skill instructs the agent to generate and write PHP scripts (tests) to the filesystem. This is the intended primary function for a development scaffolding tool and is performed locally.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:55 PM
Security Audit — agent-trust-hub — pest-testing