building-static-site-rss-feeds

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Includes documentation and examples for using curl to interact with the W3C Feed Validator, an established service for validating feed syntax.
  • [INDIRECT_PROMPT_INJECTION]: The skill outlines a methodology for converting markdown-based content into structured web feeds, creating an attack surface for indirect injection.
  • Ingestion points: The implementation logic in references/IMPLEMENTATION.md describes reading content from local files in the content/posts directory.
  • Boundary markers: The provided templates and logic do not specify the use of delimiters or instructions to prevent the agent from following directions embedded within the site's content.
  • Capability inventory: The implementation requires capabilities for file system access (os.WriteFile, os.Create) and web serving via HTTP.
  • Sanitization: The skill recommends using XML CDATA sections to escape HTML content and provides a programmatic validation step using xml.Unmarshal to ensure well-formedness.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 02:41 AM
Security Audit — agent-trust-hub — building-static-site-rss-feeds