wget-reader

Fail

Audited by Snyk on Feb 16, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.80). The skill instructs use of wget with arbitrary --header flags (and would be used to call authenticated APIs), which encourages embedding Authorization/API tokens directly into generated commands so the LLM would need to output secret values verbatim if a user provides them.

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

  • Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and displays arbitrary public web content using wget (e.g., the "wget -qO- """ example in SKILL.md), meaning the agent will ingest untrusted third-party pages or API responses that could carry indirect prompt injections.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 02:39 AM