readable-mdn

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches documentation content from the official mdn organization repositories on GitHub (raw.githubusercontent.com/mdn/content and raw.githubusercontent.com/mdn/translated-content). These are well-known, trusted sources for web development documentation.
  • [COMMAND_EXECUTION]: The skill uses the curl utility to download Markdown files to a temporary location (/tmp/mdn.md). The execution is limited to retrieving content from defined Mozilla documentation paths.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation which could theoretically contain malicious instructions.
  • Ingestion points: Remote content is downloaded via curl from raw.githubusercontent.com/mdn and read into the agent's context from /tmp/mdn.md in SKILL.md.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Uses curl for network access and file system operations (writing and reading in /tmp) as defined in SKILL.md.
  • Sanitization: No specific sanitization or filtering of the retrieved Markdown is performed, relying on the reputation of the official MDN repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 02:54 AM