bifrost
bifrost is a Runtime diagnostics & profiling skill for AI agents, published by bifrost-proxy in the bifrost repository on GitHub. Skillspace rates bifrost F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.
Unsafe. This skill has patterns associated with malicious or dangerous behaviour. We do not recommend running it.
使用 bifrost 命令行工具管理代理生命周期、规则、Group 规则、证书、脚本、系统代理、运行时配置与流量查询(含 JSONPath/header 等值/时间窗高级过滤、search --include 直接挂 body/headers、traffic 批量 get、auth-status JWT/Cookie 诊断、export curl/fetch/HAR、replay + JSON Patch、capture wait 等下一条请求、status --format json),以及远程调用(remote shell 执行、授权管理、远程流量排查)。当用户提到以下任意场景时触发:1) 启动/停止/检查 bifrost 代理;2) 配置 TLS 拦截(域名白名单、应用白名单);3) 调试或管理规则/Group 规则/脚本;4) 查看流量记录、搜索请求;5) 通过一个少于 6 位的数字 ID 获取请求详情(如「获取 57544 的详情」「获取 47544 请求的内容」「查看 12345」等);6) 修改 values/config/CA 证书/系统代理;7) 远程调用:连接/断开远端 Bifrost、远程执行命令(shell exec)、管理 Shell Access 策略与 Profile、管理远程授权(grant);8) 诊断 JWT/Cookie 过期/重放请求/导出 curl/fetch/HAR/等待下一条匹配请求/批量取多条 traffic。常见触发表述:'使用 bifrost 获取 xxxxx 的详情''获取 xxxxx 的请求内容''查看 xxxxx 的内容''bifrost traffic get xxxxx''导出 xxxxx 为 curl''重放 xxxxx 这条请求''看下 xxxxx 的 JWT 还有效吗''等下一条 POST xxxxx 的请求''远程执行命令''管理远程授权' 等、远程文件操作(file.read/list/stat/glob/search/hash/upload/download)。
- Grade
- F
- Quality
- 15 / 100
- Safety
- Unsafe
- GitHub stars
- 104
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 69 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Critical-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- pipe remote script to shell
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.