wordpress-news-writing
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the WordPress brand writing style guide from the official WordPress GitHub repository (github.com/WordPress/marketing). This fetch targets a trusted vendor resource necessary for the skill's stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content for drafting and editing tasks, creating a standard surface for indirect prompt injection.
- Ingestion points: User instructions, drafts, and existing copy provided in the chat context for revision or adaptation.
- Boundary markers: No explicit delimiters are used to isolate user input from the agent's instructions.
- Capability inventory: The skill's capabilities are limited to drafting text and fetching Markdown references; it lacks access to sensitive files, command execution, or network exfiltration tools.
- Sanitization: The skill does not implement specific sanitization or filtering for the processed input data.
Audit Metadata