ai privacy skills

6 tagged ai privacy, measured the same way as everything else here.

Browse within: AI Safety 5

privacy-mask

01

fullstackcrew-alpha/privacy-mask

Skill Claude CodeCodex

Mask, redact, anonymize and censor sensitive information (PII) in screenshots and images — phone numbers, emails, IDs, API keys, crypto wallets, credit cards, passwords, and more. Uses OCR (Tesseract + RapidOCR) with 47 regex rules and optional NER (GLiNER) to detect private data and applies blur/fill redaction…

11 5mo ago A 113 tokens original MIT

audit

02

sonomoshq/Canary

Skill Claude CodeCodex

Use when the user wants to check installed Claude Code plugins, skills, agents, or MCP configs for leaked secrets or suspicious/exfiltration patterns.

2 1mo ago A 31 tokens original MIT

scan

03

sonomoshq/Canary

Skill Claude CodeCodex

Use when the user worries they pasted a secret, asks "did I leak anything?", or wants a full-history privacy audit — the automatic scan only covers the latest message.

2 1mo ago A 36 tokens original MIT

token

04

sonomoshq/Canary

Skill Claude CodeCodex

Use when the user wants to plant a decoy/tripwire secret, create a canary token, or check whether a planted token has been leaked to Claude.

2 1mo ago A 35 tokens original MIT