Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Privacy Redactor — measured AI agent skill | DecimalAI

stijnman/privacy-redactor

SkillScore100Maintained

Detects and redacts PII in inputs and outputs before external actions. Use w hen the user says redact PII, privacy check, or sanitize this. Scans emails, phones, names, addresses. Routes high-risk to hitl-approver. Triggers: reda ct PII, privacy check, sanitize this, remove personal data.

by stijnman

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Security & AppSec pack

decimalai skills pull stijnman-privacy-redactor

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-privacy-redactor/SKILL.md

Raw file: /s/stijnman-privacy-redactor/SKILL.md ↗ · machine-readable summary at /s/stijnman-privacy-redactor.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

Yes — +64% lift+7% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	72%	0%
case-02	✗→✓	▲ Improved	65%	0%
case-03	✗→✓	▲ Improved	64%	0%
case-04	✗→✓	▲ Improved	86%	0%
case-05	✗→✓	▲ Improved	41%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stijnman / grok-custom-skills

.grok/skills/privacy-redactor/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Privacy Redactor

When to Use

User says redact PII or task matches this capability
User says privacy check or task matches this capability
User says sanitize this or task matches this capability
User says remove personal data or task matches this capability

Workflow

Scan text for PII patterns: email, phone, SSN, address, full names.
Replace with tokens: EMAIL], PHONE], NAME], ADDRESS].
List redactions in summary for user review.
If external send requested, run hitl-approver after redaction.

Integrations

hitl-approver
whatsapp-auto-responder
memory-sanitizer

Error Handling

| Failure | Response | |---------|----------| | Over-redaction | Preserve structure; only redact confirmed PII. | | Missed PII | Run second pass on capitalized tokens and @ symbols. |

Gotchas

Never log raw PII to external services after redaction.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Want to see if stijnman/privacy-redactor would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.