markdown-for-agents

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides documentation for interacting with the official Cloudflare API using curl to enable specific features. These commands use standard placeholders for authorization tokens and zone identifiers, which is a safe practice for technical documentation.
  • [EXTERNAL_DOWNLOADS]: Mentions tools such as llms_txt2ctx (pip) and plugins for VitePress/Docusaurus. These are presented as standard ecosystem tools for implementing the llms.txt specification and are referenced in a neutral, informative context.
  • [PROMPT_INJECTION]: Instructions contain no attempts to override system prompts or bypass safety filters. The language is focused on technical implementation and best practices for structured data.
  • [SAFE]: The skill follows established industry standards for metadata (JSON-LD) and site discoverability (llms.txt). No evidence of obfuscation, data exfiltration, or unauthorized persistence was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 09:22 AM
Security Audit — agent-trust-hub — markdown-for-agents