wp-abilities-api

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to search the repository for existing PHP and JavaScript code patterns related to the Abilities API.
  • Ingestion points: Repository files searched for strings like wp_register_ability and wp-abilities/v1 in SKILL.md (Step 2).
  • Boundary markers: The instructions do not specify using delimiters or warnings to ignore malicious instructions within the source code being analyzed.
  • Capability inventory: The agent is tasked with writing new registration logic and using WP-CLI/Node.js based on the search results.
  • Sanitization: No explicit sanitization of discovered code is required before using it as a template for new registrations.
  • [COMMAND_EXECUTION]: The skill requires the use of bash and WP-CLI for certain workflows, which is standard for WordPress development and maintenance environments.
  • [EXTERNAL_DOWNLOADS]: The skill references the @wordpress/abilities package, which is an official package maintained by the WordPress organization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 02:49 PM
Security Audit — agent-trust-hub — wp-abilities-api