agentleFS
Sign inStart free
mguttmannmguttmann/code-audit-suite/skills/bearer-privacy/SKILL.md

bearer-privacy

Skill0 starsChanged 5 months agoMITView on GitHub

This skill should be used when the user asks to "run Bearer", "scan for PII", "Datenschutz prüfen", "DSGVO/GDPR check", "find sensitive data flows", "PII/PHI scan", "privacy risk", or wants to know where personal/health data flows through the code. Runs Bearer in Docker to classify and trace sensitive data, processed directly in Claude Code.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Default scanner is sast (security + privacy rules).

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Bearer Privacy

Purpose

Bearer adds a dimension orthogonal to SonarQube and the pure taint engines: it classifies 120+ sensitive data types (PII/PHI) and traces where that data flows — a privacy/GDPR (DSGVO) lens, not just vulnerability classes. It answers "does personal data reach a log, a third-party API, or an unencrypted store?", which neither SonarQube nor a generic SAST tool reports.

This is unique coverage, not a duplicate of any other skill.

Core Workflow (drive to zero)

  1. Scan:
    ~/.claude/skills/bearer-privacy/scripts/scan.sh [TARGET_DIR]
  2. For each finding, fix the data-handling root cause: stop logging the sensitive field, encrypt it at rest/in transit, mask/redact it before it leaves the system, or remove the unnecessary collection. Bearer maps findings to data categories (e.g. "Personal Data", "Sensitive Data") and rules (e.g. data sent to third party, stored unencrypted, leaked in logs).
  3. Re-run until the scan exits 0.

Notes

  • Default scanner is sast (security + privacy rules). BEARER_SCANNER=secrets runs Bearer's secret detection instead — prefer the dedicated secrets-scan skill for that.
  • Adjust the failing threshold with BEARER_SEVERITY (default critical,high); review medium/low informationally.
  • JSON/SARIF output for parsing: BEARER_FORMAT=json scan.sh [DIR].
  • Bearer's CLI is free for internal use (Elastic License 2.0); only the hosted management plane is commercial. This skill uses the CLI only.

Resources

  • scripts/scan.sh — runs bearer scan against a directory, exit 1 on findings at/above the severity threshold. Env: BEARER_FORMAT, BEARER_SCANNER, BEARER_SEVERITY.

Download now (ZIP)

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