magento-testing

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill directs the agent to fetch documentation from Adobe's official developer portal (developer.adobe.com), a well-known technology provider. This is consistent with its purpose of guiding Magento 2 development.
  • [SAFE]: Test execution commands like vendor/bin/phpunit and vendor/bin/mftf are standard in the Magento ecosystem and represent normal development activity.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive file access, credential usage, or suspicious network transmissions were detected.
  • [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface due to fetching external documentation while maintaining write and command execution capabilities. The risk is considered safe as the source is a trusted service.
  • Ingestion points: Documentation fetched via WebFetch from developer.adobe.com (SKILL.md).
  • Boundary markers: Not explicitly defined for the external content.
  • Capability inventory: Bash, Write, and Edit tools are listed in the skill frontmatter.
  • Sanitization: No specific sanitization of external documentation is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 06:10 AM