write-article

Fail

Audited by Snyk on Jun 17, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). 不安全:指令要求将用户提供的原始草稿“原样保留”并写入输出文件,同时读取 $ARGUMENTS 指定的任意文件并包含其内容——这会强制 LLM 在输出中逐字复现用户或文件中可能包含的 API 密钥/密码/令牌等敏感信息,存在凭证外泄风险。

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

  • Third-party content exposure detected (high risk: 0.85). 该 skill 的运行时会执行 WebSearch/WebFetch 来抓取“权威来源”网页内容,并把抓取到的网页正文/摘要作为可读文本进入 LLM 上下文;这些网页属于公开网络内容(outsider-authored free text)。

Issues (2)

W007
HIGH

Insecure credential handling detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
HIGH
Analyzed
Jun 17, 2026, 06:40 PM
Issues
2