wordpress-writer-news-event-recap

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and analyze content from external, untrusted sources provided by the user, creating a surface for potential indirect prompt injection attacks. \n
  • Ingestion points: Content is ingested from user-provided 'WordCamp website URL', 'Schedule URL', 'Event news posts URL', and 'Keynote video links or captions' (SKILL.md). \n
  • Boundary markers: While no explicit text delimiters are defined, the skill mandates a 'Required source pass before drafting' to separate content extraction from the final text generation (SKILL.md). \n
  • Capability inventory: The agent uses browsing and HTTP fetch tools to retrieve content from the provided URLs. \n
  • Sanitization: The instructions include a 'tone pass' and 'clarity pass' that guide the agent to reframe provocative or negative source framing into constructive public copy, providing a layer of behavioral defense (SKILL.md). \n- [EXTERNAL_DOWNLOADS]: The skill fetches authoritative writing and brand guidelines from the WordPress organization's public GitHub repository. \n
  • Evidence: References raw markdown content from 'https://raw.githubusercontent.com/WordPress/marketing/main/shared/references/'. This is a well-known and expected source for a WordPress-focused writing skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 06:42 PM