Skill 审计报告
raptor-loop-hunt 审计报告.
Autonomous, looping, multi-altitude security vulnerability hunting for source code using RAPTOR's inventory-first generate-judge-verify methodology. Use by default when the user points to a repo, service, app, module, or directory and asks to audit, pentest, security-review, find bugs, or find anything exploitable. Depth cues such as go deep, find every bug, exhaustive, maximum coverage, keep hunting, verified not guessed, auto-research, or file/function-by-function strengthen the match, but a plain source-code security audit also qualifies. Do not use for webserver/config-only audits, one known-CVE reproduction, a one-file/function sanity check, dependency/SCA lookup, PR or style review, debugging one specific crash, or attack-surface mapping without vulnerability hunting.
OpenAgentSkill 信任评分
OpenAgentSkill 信任评分
Trust Score 帮助 Agent 在安装前判断一个 Skill 是否足以进入候选清单。
GitHub 采用度
信息62
217 个 GitHub Stars
Star/Fork 活跃度
警告57
217 个 Star，18 个 Fork; 当前元数据中没有议题活跃度信息
近期维护
通过88
距上次推送 1 个月
许可证清晰度
通过86
MIT
README/SKILL.md 完整度
信息76
公开元数据需要更完整的 README/SKILL.md 上下文
依赖与运行时风险
信息72
凭据或环境变量访问
安装可用性
通过92
npx skills add dinosn/raptor-loop-hunt --skill raptor-loop-hunt
安装命令安全性
通过92
标准软件包或运行时安装路径
权限范围
警告60
secrets or environment access, filesystem or document access
仓库证据
通过86
https://github.com/dinosn/raptor-loop-hunt/blob/main/SKILL.md
审查状态
通过88
可用 AI 审查数据
Agent 验证结果
信息54
暂未有 Agent 结果数据
检查项
安装与采用审查
安装路径
92
npx skills add dinosn/raptor-loop-hunt --skill raptor-loop-hunt
仓库
88
https://github.com/dinosn/raptor-loop-hunt/blob/main/SKILL.md
许可证
86
MIT
维护
88
距上次推送 1 个月
AI 审查
88
Approved with no listed issues
README/SKILL.md 完整度
84
Usable description available
依赖风险
72
凭据或环境变量访问
安装命令安全性
92
标准软件包或运行时安装路径
权限范围
60
secrets or environment access, filesystem or document access
Star/Fork 活跃度
57
217 个 Star，18 个 Fork; 当前元数据中没有议题活跃度信息
采用度
68
217 个 GitHub Stars
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
警告
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- Financial research output is not financial advice; require human review before any live investment decision.
- Quality score needs review
- Permission surface needs review: secrets or environment access, filesystem or document access
- Stars/forks activity: 217 stars, 18 forks; issue activity unavailable in current metadata
- Permission surface: secrets or environment access, filesystem or document access
方法
本报告综合公开元数据、AI 审查输出、仓库活跃度、安装就绪度、OpenAgentSkill 事件、质量评分、信任检查和 Agent 安全门槛；它不是完整的源代码安全审计。
对比相近选项