wp-plugin-lifecycle

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides standard documentation and code snippets for WordPress development. No malicious instructions, obfuscation, or unauthorized persistence mechanisms were identified.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by instructing an agent to process and generate code for database operations and file management.
  • Ingestion points: Analyzes plugin scaffolding and PR reviews as described in the 'When to use' section of SKILL.md.
  • Boundary markers: None explicitly defined in the provided instructions.
  • Capability inventory: Performs database writes and table drops (dbDelta, $wpdb->query), manages site options (add_option, delete_option), handles WordPress cron schedules (wp_schedule_event, wp_unschedule_hook), and modifies user roles (add_cap, remove_cap).
  • Sanitization: Present; the reference patterns in references/uninstall-and-multisite.md explicitly use $wpdb->prepare() and $wpdb->esc_like() to prevent SQL injection.
  • [DATA_EXFILTRATION]: The skill focuses on managing internal WordPress data (options, metadata, and custom tables). No network operations or commands that send data to external or non-whitelisted domains were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 07:06 PM
Security Audit — agent-trust-hub — wp-plugin-lifecycle