competition-web-runtime
Fail
Audited by Snyk on Jun 20, 2026
Risk Level: CRITICAL
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). 该技能明确要求“记录精确的请求、响应、headers、cookies 和 body”等数据并保留证据,这会导致 LLM 必须处理并可能回显会话令牌/Cookie/敏感 header 等机密值,存在高风险的凭证外泄。
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 1.00). 该技能包包含明确的利用说明(“Cookie HMAC 密钥复用 → 后台认证绕过”),并附带可执行的 Python/JavaScript 示例和逐步攻击流程,用于伪造管理员 Cookie、利用 URL token 作为 HMAC 密钥并实现未授权的权限提升与后台绕过,属于高风险的恶意利用向量。
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). 该技能的运行时工作流要求“Inspect entry HTML/boot scripts/runtime config/route registration”并“Record exact host/path/query/headers/cookies/body for decisive requests”,这些步骤会读取并把目标站点返回的页面/脚本/配置等外部内容(由第三方网站/服务端生成)作为可读文本进入LLM上下文,从而存在间接提示注入风险。
HIGH W008: Secret detected in skill content (API keys, tokens, passwords).
- Secret detected (high risk: 1.00). 分析理由:文档中直接出现一个高熵随机字符串 "/access/blD4QO5On1O7G3M47ZxE4u93Qw4dr1ra",并在示例中把提取出的 token 明确写为 "blD4QO5On1O7G3M47ZxE4u93Qw4dr1ra"。该值不是占位符,具有随机高熵特征,且文档示例中将其作为 HMAC 签名密钥使用,因而符合“实际可用凭据”的定义,应被标记为秘密。其他示例(如 "已知的token"、常见 cookie 名称、base64 示例等)均为占位或演示用途,按规则忽略。
Issues (4)
W007
HIGHInsecure credential handling detected in skill instructions.
E006
CRITICALMalicious code pattern detected in skill scripts.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W008
HIGHSecret detected in skill content (API keys, tokens, passwords).
Audit Metadata