codeception-skill

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the Codeception testing framework and its associated modules (including WebDriver, REST, and DB) from the official PHP package registry (Packagist) using composer.
  • [COMMAND_EXECUTION]: Recommends standard PHP project initialization and test execution commands using composer and the codecept CLI tool.
  • [INDIRECT_PROMPT_INJECTION]: As a code-generation assistant, the skill ingests user-provided requirements to produce PHP tests; while this creates an attack surface for indirect injection, it is the intended primary purpose of the skill.
  • Ingestion points: User-provided descriptions of test scenarios and application workflows.
  • Boundary markers: No explicit delimiter boundaries are defined in the provided templates.
  • Capability inventory: Generation of PHP source code and shell command execution instructions.
  • Sanitization: Relies on model-level safeguards as no explicit sanitization logic is provided in the markdown.
  • [CREDENTIALS_UNSAFE]: Demonstrates secure handling of sensitive data by using environment variable placeholders (%LT_USERNAME%, %LT_ACCESS_KEY%) for authentication to vendor cloud infrastructure, rather than hardcoding credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 09:34 PM