No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by CheshireMew · Codex Skill · ★ 60
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Price-action-analysis safe to install? View the security audit →
价格行为分析 Codex Skill 这个仓库是一个 Codex skill，用于把用户提供的 K 线截图或 OHLC 图表数据，制作成带通道、区间、箭头、关键价位、形态标签和交易计划的价格行为标注分析图。 能做什么 基于 Al Brooks / 阿布价格行为学读取 K 线背景、市场周期、通道、交易区间、突破、失败突破和反转尝试。 在原始图表上叠加确定性标注，不重画 K 线，不编造价格。 同一张图里同时交付历史复盘层和当前交易计划层。 输出多头触发、空头触发、失效位置、目标区域、不交易条件和风险提醒。 目录结构 连接到 Codex 把仓库目录链接到 Codex 用户 skill 目录： 如果当前 Windows 环境不允许创建符号链接，可以改用目录联接： 连接完成后，新开的 Codex 会在可用 skills 中看到 。 使用方式 在 Codex 中提供 K 线截图后调用： 渲染脚本也可以单独运行： 交付标准 图上必须有历史复盘层和当前计划层。 历史复盘不能只写形态名称，必须说明当时证据、当时计划、失效点和后续验证。 当前计划必须包含触发条件、止损或失效、目标区域和不交易条件。 图上文字不能遮挡关键 K 线
| Stars | 60 |
| Forks | 12 |
| Language | Python |
| Category | Codex Skill |
| License | MPL-2.0 |
| Quality Score | 56.56481216746/100 |
| Open Issues | 1 |
| Last Updated | 2026-07-30 |
| Created | 2026-06-30 |
| Platforms | codex, python |
| Est. Tokens | ~6k |
Explore other popular codex skill tools:
Price-action-analysis is Codex skill for annotated price action chart analysis. It is categorized as a Codex Skill with 60 GitHub stars.
Price-action-analysis is primarily written in Python.
You can find installation instructions and usage details in the Price-action-analysis GitHub repository at github.com/CheshireMew/Price-action-analysis. The project has 60 stars and 12 forks, indicating an active community.
Price-action-analysis is released under the MPL-2.0 license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: