一键导入
pii
Scan for personally identifiable information
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Scan for personally identifiable information
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Execute an automation playbook — deterministic scripts with LLM error recovery
Check compliance against Punt Labs standards
Scaffold missing files for a Punt Labs project
LLM-powered standards reconciliation for a Punt Labs project
| name | pii |
| description | Scan for personally identifiable information |
| disable-model-invocation | true |
Scan a repository for personally identifiable information (emails, local paths, hostnames).
If the user provided a project path as an argument, use it. Otherwise default to .. The user may also pass --staged for pre-commit use or --config FILE for a custom config.
Run in the shell:
punt pii <path> [--staged] [--config FILE]
using the path and flags from the user's input.
Report the output to the user. If findings are detected, explain each category and suggest remediation (replace personal emails with org identity, use relative paths, etc.).
If the user wants to configure allowlists, point them to [tool.punt.pii] in pyproject.toml or .punt-pii.toml for non-Python projects.