← All mods

Mod · Context

Privacy

Redacts detected secrets and chosen personal-data patterns before a request reaches the model.

Install

OMD+: installed and off by default. Manage it from /mods.

OMD Core: install it, then turn it on:

$ omd install omd_privacy
$ omd mods enable omd_privacy

What it does

  • Uses stable placeholders, and refuses a request it can’t safely redact.
  • Asks before shell commands read sensitive paths. Configure it with /privacy.

Capabilities

You approve these when you trust the mod, and again whenever its source changes.

  • approvals
  • commands
  • middleware
  • request_policy
  • store

Settings

KeyValuesDefault
secretsarray["private_key","aws_access_key","github_token","gitlab_token","slack_token","stripe_key","ai_api_key","google_api_key","npm_token","jwt","bearer_token","url_credentials","assigned_secret"]
piiarray[]
scopesarray["prompt","context","tools","replies"]
pathsask · deny · offask
sensitive_pathsarray[".env",".env.*","*.pem","*.key","*.p12","*.pfx","id_rsa*","id_dsa*","id_ecdsa*","id_ed25519*",".ssh/",".gnupg/",".aws/credentials",".docker/config.json",".kube/config",".netrc",".npmrc",".pypirc",".pgpass",".git-credentials"]
exemptarray["path:.env.example","path:.env.sample","path:.env.template","path:*.pub"]
unscannedallow · denyallow