http-request

Fail

Audited by Snyk on Mar 1, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill's examples and auth options explicitly show embedding tokens, API keys, and passwords directly in command lines and headers (e.g., --auth bearer:TOKEN, --header "X-API-Key: secret"), which would require the LLM to include secret values verbatim in its output.

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly lets the agent make GET/POST requests to arbitrary http/https URLs (see SKILL.md examples like https://jsonplaceholder.typicode.com and the request.sh/index.js code that accept external URLs and return/format response data), so it fetches untrusted public web content that the agent will read and could materially influence subsequent behavior.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 1, 2026, 05:11 AM