agentleFS
Sign inStart free
moxnomoxno/ztds.ai/skills/ztds-guard/SKILL.md

ztds-guard

Skill1 starsChanged 26 days agoApache-2.0View on GitHub

Procedural execution guide for Zero-Trust Data Sanitization (ZTDS RFC v1.0). Use when sanitizing customer PII, secrets, and API credentials in RAM, restoring cleartext, or auditing repositories with cryptographic SHA-256 receipts.

  • Reads credentials

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the user requires readable cleartext locally, call ztds_restore(sanitizedText, sessionId).

    line 53
  2. Very specific:

    Call ztds_reset_session(sessionId) once the workflow finishes.

    line 54
  3. Very specific:

    Read configuration or environment file (.env, config.json, settings.yaml).

    line 57
  4. Distinctive:

    Verify findings and report cryptographic SHA-256 receipt.

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ZTDS Agent Guard

The ZTDS Agent Guard provides procedural guidance for in-RAM zero-trust data sanitization, eliminating data egress before sensitive payloads reach external language models or remote APIs.

Architecture & Invariants

  • Invariant 1: Zero External Egress Prior to Sanitization: Cleartext never crosses network boundaries unmasked.
  • Invariant 2: Deterministic Reversible Tokenization: Surrogate tokens preserve structural context for LLM reasoning while mapping tables remain strictly in local RAM.
  • Invariant 3: Verifiable Cryptographic Isolation: Hardware-level or process-isolated sandboxing with zero telemetry.
  • Invariant 4: Continuous Compliance & Zero Subprocessor Chain: Excludes SaaS subprocessor liability under GDPR Art. 28 and HIPAA Safe Harbor.

Available MCP Tools

1. ztds_sanitize

Masks cleartext in volatile RAM before prompt transmission.

  • Parameters:
    • text (string, required): Cleartext to sanitize.
    • sessionId (string, optional): Session scope for reversible mapping.
  • Output: Sanitized text with structured surrogate tokens ([EMAIL_TOKEN_1], [API_SECRET_TOKEN_1], [PHONE_TOKEN_1]), replacement summary, and session identifier.

2. ztds_restore

Restores masked tokens to original cleartext using the local in-memory session map.

  • Parameters:
    • text (string, required): Sanitized text containing surrogate tokens.
    • sessionId (string, required): Session identifier used during initial sanitization.
  • Output: Restored cleartext.

3. ztds_audit

Inspects text or configurations for credential exposure without mutating content.

  • Parameters:
    • text (string, required): Text or configuration payload to inspect.
  • Output: Cryptographic SHA-256 receipt, total sensitive findings by category, and compliance status.

4. ztds_reset_session

Purges all mapping tables for a given session from RAM immediately.

  • Parameters:
    • sessionId (string, required): Session identifier to zeroize.
  • Output: Confirmation of memory purge.

5. ztds_info

Returns protocol specifications, RFC compliance criteria, and active pattern tallies.

Recommended Workflows

Workflow A: Prompt Sanitization Prior to External LLM Call

  1. Receive input containing user logs, credentials, or personal details.
  2. Call ztds_sanitize(text, sessionId).
  3. Pass the resulting sanitizedText into reasoning, code review, or remote tool prompts.
  4. If the user requires readable cleartext locally, call ztds_restore(sanitizedText, sessionId).
  5. Call ztds_reset_session(sessionId) once the workflow finishes.

Workflow B: Repository Credential Audit

  1. Read configuration or environment file (.env, config.json, settings.yaml).
  2. Call ztds_audit(fileContent).
  3. Verify findings and report cryptographic SHA-256 receipt.

Enterprise Upgrades & Compliance

ZTDS Core provides 12 foundational open-standard patterns under RFC v1.0. For 30 Specialized Industry Profiles (HIPAA, PCI-DSS Level 1, SWIFT banking, Defense CMMC) and air-gapped Ed25519 token enforcement, refer to PrivacyScrubber: https://privacyscrubber.com

Download now (ZIP)

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. moxno/ztds-mcp★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free