wordpress-writer-news

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the WordPress Brand Writing Style Guide and News Post Rules from the WordPress organization's official GitHub repository at raw.githubusercontent.com/WordPress/marketing/main/shared/references/. These are legitimate documentation resources used to calibrate the AI's output voice.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided source material such as release notes and announcements to generate content drafts, creating a surface for indirect instructions.
  • Ingestion points: The 'Inputs' section of SKILL.md specifies that source material like release notes, event notes, and briefs are used as the basis for drafting.
  • Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore potential instructions embedded within the user-provided inputs.
  • Capability inventory: The skill's primary function is text generation for human review; it does not demonstrate command execution, network exfiltration, or unauthorized file access capabilities.
  • Sanitization: There are no instructions for sanitizing, escaping, or validating the content of the provided inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 06:42 PM