create-tldr-page

Warn

Audited by Snyk on Feb 25, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly requires and fetches public documentation URLs (see "Prompt Parameters" → URL and "Usage/Syntax" showing "/create-tldr-page #fetch " and the note "If one or more URLs are passed... apply #tool:fetch"), so the agent ingests and interprets arbitrary third‑party webpages to generate TLDR pages, allowing untrusted content to influence its behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill requires fetching a user-supplied documentation URL at runtime (e.g., it explicitly calls #fetch on URLs such as https://raw.githubusercontent.com/jhauga/tldr/refs/heads/main/pages/common/git.md or any arbitrary docs URL) and injects that fetched content into the agent context to generate the tldr, so external content can directly control the agent's output.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 25, 2026, 05:26 AM