agentleFS
XakkiXakki/ai-agents-skills/skills/security-privacy-review/SKILL.md

security-privacy-review

Skill6 starsChanged 3 months agoMITView on GitHub

Review secret handling, redaction, no-read and privacy claims across application boundaries. Use for credential loading, sensitive-data redaction or "secrets never reach logs" claims. RU: приватность, секреты в логах.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Privacy boundary review

Use for an authorized review of credential loading, sensitive-data redaction, or claims that source bodies, identifiers or secrets do not cross persistence, logs, responses, telemetry, filesystem or transport boundaries. Define the allowed scope first and distinguish no body read, no disclosure, and no mutation: evidence of one is not proof of the others.

Trace each representation before and after normalization, hooks, hashing, storage and output. For telemetry include logs, spans, events, metric labels and every exporter separately. Redaction must happen before any forbidden boundary; sanitizing a final log cannot undo earlier exposure. Review exact configured sinks and use synthetic sentinels, keeping secret values and raw payloads out of command output, reports and delegated work.

For dotenv and credential source precedence use configuration sources; for runtime and no-read proof use privacy evidence; for a source-only credential inventory use source evidence. This review does not authorize reading secret stores, testing live credentials, changing accounts or modifying code.

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.