wordpress
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external WordPress sites, which could contain malicious instructions meant to influence the agent's behavior.\n
- Ingestion points: The skill reads WordPress site content, posts, pages, media, comments, and terms (
SKILL.md).\n - Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions when reading data from the external site.\n
- Capability inventory: The agent can create, update, and delete content, media, comments, and settings, as well as publish standalone HTML files (
SKILL.md).\n - Sanitization: Partially present. The instructions state that 'Scripts are rejected for standalone HTML publish' (
SKILL.md), but there is no mention of sanitizing general content or comments retrieved from the site.
Audit Metadata