blog
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or unauthorized data access behaviors were found. The skill includes appropriate safety warnings for users to verify AI-generated content and recommends reputable security practices for managed blogs.
- [PROMPT_INJECTION]: The skill has a standard surface for indirect prompt injection due to its core function of processing user-provided topics and instructions for publication. • Ingestion points: User-provided blog topics, target keywords, and platform-specific instructions in SKILL.md. • Boundary markers: No explicit delimiters or guardrail instructions to isolate user-supplied content are present. • Capability inventory: Capability to automate publishing to WordPress sites using the vendor's 'WordPress Cowork' connector. • Sanitization: The instructions do not specify any validation or sanitization routines for user input before generation.
Audit Metadata