wp-wpcli-and-ops

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local JavaScript file using Node.js to inspect the environment.
  • Evidence: node skills/wp-wpcli-and-ops/scripts/wpcli_inspect.mjs in SKILL.md.
  • [COMMAND_EXECUTION]: The skill invokes the wp command-line tool to perform various WordPress operations including database exports and site modifications.
  • Evidence: wp db export, wp search-replace, wp plugin *, etc. in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from WordPress installations that may contain untrusted user-generated content.
  • Ingestion points: Data enters the agent context through wp subcommands that read from the WordPress database (wp db export) or site content (wp search-replace).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions are present in the skill body when handling database or site data.
  • Capability inventory: The agent has the capability to execute shell commands (node, wp) and write to the file system (backups).
  • Sanitization: No specific sanitization or filtering logic is described for the data processed by WP-CLI commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 02:58 PM
Security Audit — agent-trust-hub — wp-wpcli-and-ops