wp-wpcli-and-ops

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The diagnostic utility scripts/wpcli_inspect.mjs utilizes node:child_process.spawnSync to execute the wp (WP-CLI) binary for verifying the WordPress environment and retrieving site configuration.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by reading potentially attacker-controlled data from the database.\n
  • Ingestion points: Site configuration values such as siteurl and home are retrieved via wp option get in scripts/wpcli_inspect.mjs.\n
  • Boundary markers: The script outputs the collected data in a structured JSON format, which provides basic separation of data from instructions.\n
  • Capability inventory: The skill enables high-privilege WordPress operations including database resets, imports, and search-replace functions as described in SKILL.md and references/safety.md.\n
  • Sanitization: The retrieved database values are incorporated into the JSON output report without validation or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 03:03 PM
Security Audit — agent-trust-hub — wp-wpcli-and-ops