Skills
Navigate
skills/kylebrodeur/wordpress-agent-kit/wp-wpcli-and-ops/Gen Agent Trust Hub

wp-wpcli-and-ops

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/wpcli_inspect.mjs uses the node:child_process module to execute wp CLI commands for inspection purposes. Evidence: const out = spawnSync("wp", args, { encoding: "utf8" }); in scripts/wpcli_inspect.mjs.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads data from the WordPress database (specifically the siteurl and home options) which is then returned to the agent's context. 1. Ingestion point: WordPress database values retrieved via wp option get in scripts/wpcli_inspect.mjs. 2. Boundary markers: None present; the raw output of the WP-CLI command is returned as part of a JSON object. 3. Capability inventory: The skill utilizes subprocess calls (spawnSync) to manage the WordPress site. 4. Sanitization: No sanitization is performed on the data retrieved from the database before it is provided to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 07:26 PM