wp-astrojs

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill ingests data from external WordPress sources and provides the agent with tools to create, update, and delete content, which could be abused if malicious instructions are embedded in the fetched data.\n- [PROMPT_INJECTION]: Mandatory Evidence Chain for Indirect Injection:\n
  • Ingestion points: WordPress content is fetched via wordPressPostLoader and wordPressPostStaticLoader as defined in SKILL.md.\n
  • Boundary markers: There are no explicit instructions or delimiters to isolate untrusted WordPress content from the agent's logic.\n
  • Capability inventory: The skill exposes administrative server actions including createCreatePostAction, createUpdatePostAction, and createDeletePostAction (SKILL.md).\n
  • Sanitization: The integration uses Zod schemas for structural validation of data, but this does not mitigate natural language instruction injection within content fields.\n- [SAFE]: The skill uses wp-astrojs-integration, which is a vendor resource authored by JUVOJustin.\n- [SAFE]: Configuration of the WordPress endpoint relies on environment variables (import.meta.env.PUBLIC_WORDPRESS_BASE_URL), following security best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 09:43 AM