wp-block-development

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides comprehensive guidance for WordPress Gutenberg block development, adhering to official best practices and using standard tools. No malicious patterns were detected in the instructions or scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes block.json files from the local filesystem to summarize block metadata for the agent. This represents a standard surface for processing project-specific data.
  • Ingestion points: The scripts/list_blocks.mjs script reads and parses block.json files found within the local repository.
  • Boundary markers: The script parses file content as structured JSON, reducing the risk of accidental instruction following, though no explicit delimiters are added to the summarized output provided to the agent.
  • Capability inventory: The skill is configured to run local build tools, Node.js scripts, and WordPress CLI commands. It does not possess network exfiltration or arbitrary remote code execution capabilities.
  • Sanitization: Files are processed using JSON.parse(), which ensures only valid data structures are extracted and prevents the execution of raw file content during the triage and scanning phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:54 PM
Security Audit — agent-trust-hub — wp-block-development