wp-block-development
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local script
scripts/list_blocks.mjsto scan for WordPress block definitions and instructs the agent to run standard development commands such asnpm run build,wp-cli, andwp-env. - [EXTERNAL_DOWNLOADS]: The skill references and utilizes well-known WordPress development packages including
@wordpress/scripts,@wordpress/create-block, and@wordpress/envfrom official registries. - [PROMPT_INJECTION]: The skill processes untrusted project data by reading
block.jsonfiles from the target repository, creating an indirect prompt injection surface. - Ingestion points:
block.jsonfiles are scanned and read by thescripts/list_blocks.mjsscript. - Boundary markers: Data is output as structured JSON to stdout, but there are no explicit delimiters or instructions to ignore embedded content during processing.
- Capability inventory: The agent is authorized to write files, run npm scripts, and execute shell commands (wp-cli).
- Sanitization: The script uses standard JSON parsing but does not perform content validation or sanitization on strings extracted from the configuration files.
Audit Metadata