NYC

wp-block-development

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) as it processes project files and utilizes command-execution capabilities. Evidence: (1) Ingestion points: the agent reads local repository files including block.json, PHP, and JavaScript; (2) Boundary markers: no explicit markers or safety instructions are defined for these data inputs; (3) Capability inventory: the skill executes shell commands (node, npm, wp-cli); (4) Sanitization: no specific sanitization logic is described.
  • [COMMAND_EXECUTION] (SAFE): Shell commands are used for build and triage tasks consistent with official WordPress development workflows.
  • [EXTERNAL_DOWNLOADS] (SAFE): All external tool and package references (e.g., @wordpress/scripts) are directed toward trusted WordPress ecosystem organizations.
  • [NO_CODE] (SAFE): The procedure references internal triage and listing scripts that are not present in the provided skill bundle, though their described use is benign.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:08 PM