ai-content-monetization

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by interpolating it directly into prompts sent to the LLM, creating a surface for indirect prompt injection.
  • Ingestion points: The variables 'trending_topics', 'blog_post', and 'affiliate_products' in SKILL.md are ingested into the LLM context to generate content.
  • Boundary markers: The prompt templates for 'generate_blog_post' and 'generate_newsletter' do not use delimiters or instructions to ignore embedded commands in the interpolated data.
  • Capability inventory: The skill possesses write capabilities to external systems via the WordPress REST API and the Resend Email API.
  • Sanitization: No methods for escaping or validating the external content are included before it is used to populate prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 09:17 AM
Security Audit — agent-trust-hub — ai-content-monetization