agentsclimarketplace
Sign in

Llm wiki privacy redactor

Skill po4yka/llm-wiki-skills/skills/llm-wiki-privacy-redactor

Preview and plan redaction of private or sensitive content before publishing, exporting, or sending LLM-Wiki context to external models. Use for emails, tokens, internal URLs, phone numbers, private tags, and sensitive page metadata.From its SKILL.md

Install
npx -y skills add po4yka/llm-wiki-skills --skill llm-wiki-privacy-redactor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.6 KB, 468 tokens by cl100k_base, as published. Nobody here has run it

LLM-Wiki Privacy Redactor

Goal

Prevent private content from leaking through public exports, model-boundary payloads or shared reports.

When to use

  • Before exporting wiki pages, folders, or bundles to an external destination.
  • Before sending LLM-Wiki context across a model boundary to a third-party LLM.
  • When a page or raw source is tagged privacy: sensitive or marked internal.
  • When preparing a publishable report that may contain unreviewed generated claims.
  • When a redaction policy file exists and must be applied before publication.

Inputs

  • Target pages, folders or export bundle.
  • Redaction policy file if present.
  • Desired mode: preview-only or approved patch.
  • Publication or model-boundary target.

Procedure

1. Load policy

Read references/docs/security/redaction-policy.md and references/templates/redaction-policy.yml when available, and re-verify the policy file is the current version before applying it, since redaction rules can change between publications.

2. Classify content

Flag:

  • email addresses;
  • phone numbers;
  • internal URLs;
  • secret-like strings;
  • private tags;
  • pages with privacy: sensitive;
  • raw sources marked internal/sensitive;
  • unreviewed generated claims in publishable output.

3. Preview redactions

Run or recommend:

node scripts/redact-preview.mjs <path>

Show redaction candidates without modifying files.

4. Propose replacements

Use stable placeholders:

[REDACTED_EMAIL]
[REDACTED_INTERNAL_URL]
[REDACTED_SECRET]
[REDACTED_PHONE]

5. Apply only after approval

Apply changes only to an export copy unless the user explicitly asks to patch the source wiki.

Output

## Redaction summary

## Files inspected

## Findings by category

## Proposed redactions

## Export safety decision

## Review required

Safety gates

  • Do not print sensitive findings verbatim in final reports.
  • Do not mutate source wiki files by default.
  • Do not send sensitive content to external models without explicit approval.
  • Do not treat redaction as proof that publication is safe.

What ships with it: 3 files

5.9 KB alongside SKILL.md, 1 of them executable

references/

scripts/

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.