lw-lms-wp-cli-operations

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the official GitHub repository for the LW LMS plugin at https://github.com/lwplugins/lw-lms for supplemental documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill outlines a surface for processing external data (such as titles, slugs, logins, and emails) through shell-based WP-CLI commands.
  • Ingestion points: Command arguments for creating posts and resolving user/course entities in SKILL.md.
  • Boundary markers: Commands use standard CLI flag syntax to delimit inputs.
  • Capability inventory: Execution of specific, pre-defined WP-CLI commands (wp lw-lms ...).
  • Sanitization: The documentation explicitly references the use of CliResolver for entity validation and sanitize_key() for key inputs, which mitigates injection risks.
  • [SAFE]: No malicious patterns, such as prompt injection, data exfiltration, or obfuscation, were identified. The instructions align with the stated purpose of managing a WordPress plugin via its command-line interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 07:06 PM
Security Audit — agent-trust-hub — lw-lms-wp-cli-operations