woo-guard

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references official developer documentation from developer.woocommerce.com and actionscheduler.org. These are well-known, trusted resources for the WooCommerce ecosystem and are used only for informational purposes.
  • [PROMPT_INJECTION]: The skill facilitates indirect prompt injection by processing untrusted code provided by the user for review. * Ingestion points: User-provided code diffs and target files as specified in SKILL.md. * Boundary markers: Absent; the instructions do not establish delimiters to distinguish code content from agent instructions. * Capability inventory: The skill instructs the agent to analyze files (e.g., using grep) but includes no custom scripts with dangerous capabilities. * Sanitization: Absent; the input code is not sanitized or escaped before processing.
  • [SAFE]: The skill encourages the adoption of critical security practices, such as mandatory output escaping, input sanitization, nonce verification, and the use of prepared statements in SQL queries.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:44 PM
Security Audit — agent-trust-hub — woo-guard