wordpress-inspector
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's scripts use only Python's standard library, avoiding risks associated with unverified third-party dependencies.
- [SAFE]: Robust security measures are implemented to protect the user environment, including a custom XML parser that rejects DOCTYPE declarations to prevent XML External Entity (XXE) attacks and a function to defuse potential CSV injection in generated reports.
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by fetching and processing untrusted data from external WordPress sites (REST API content and sitemaps) that the agent later interprets.
- Ingestion points: External website content fetched via HTTP GET requests in scripts/wp_inventory.py.
- Boundary markers: Data is stored in intermediate CSV, JSON, and Markdown files before being read by the agent.
- Capability inventory: Network read access and local file system write access in scripts/wp_inventory.py and scripts/check_move.py.
- Sanitization: Includes specific routines to escape Markdown characters and neutralize CSV formula triggers. The XML parser also prevents the expansion of external entities.
Audit Metadata