wp-admin

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Detected an indirect prompt injection attack surface.\n
  • Ingestion points: Untrusted data enters the agent context through core/list-comments, core/list-users, and core/get-settings (SKILL.md).\n
  • Boundary markers: The instructions do not define any delimiters or specific 'ignore instructions' directives for the data retrieved from WordPress.\n
  • Capability inventory: The skill includes administrative tools such as core/update-user, core/update-settings, and core/update-plugin (SKILL.md).\n
  • Sanitization: There are no guidelines or steps provided to sanitize or validate the external content before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 01:40 PM
Security Audit — agent-trust-hub — wp-admin