wp-wpcli-and-ops
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted content from WordPress codebases, including PHP files, shell scripts, and documentation. While this creates a data ingestion surface, the skill's instructions are focused on static analysis and providing review feedback, and it does not possess autonomous capabilities (such as automated file writing or network requests) that could be leveraged for an attack.
- [SAFE]: The skill correctly identifies and warns against high-risk WordPress operations, such as destructive database commands (
wp db drop), unvalidated CLI input, and incorrect multisite scoping. It provides safe remediation patterns and templates for operational runbooks. - [SAFE]: No evidence of prompt injection, data exfiltration, or persistence mechanisms was found. The provided search patterns (ripgrep commands) are intended for local discovery of patterns in the analyzed project and do not perform unauthorized external operations.
- [SAFE]: The reference files and sample PHP code provide best-practice examples for implementing safe WP-CLI commands, emphasizing input validation, dry-run support, and batching for long-running tasks.
Audit Metadata