agentleFS
bookchaowalitbookchaowalit/platform-agent-skills/security-and-privacy/SKILL.md

security-and-privacy

Skill0 starsChanged 8 days agoApache-2.0View on GitHub

Review and improve security and privacy for Solo Empire workflows, client work, agents, integrations, secrets, authentication, permissions, personal data, dependencies, and deployments. Use before releasing a workflow or when investigating a possible exposure, unsafe tool, or boundary violation.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Keep secrets in approved environment or secret-management mechanisms.

    line 16
  2. Distinctive:

    Verify with available tests, typechecks, dependency or secret scans, migration backups, and a manual review of permissions and logs.

    line 18
  3. Distinctive:

    If an incident is suspected, contain access, revoke or rotate exposed credentials, preserve relevant evidence, assess affected data, and …

    line 19

≈ “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

Security and Privacy

Reduce exposure, make trust boundaries visible, and stop unsafe actions before they become incidents.

Review workflow

  1. Classify the data as public, internal, client-confidential, personal, regulated, or secret. Minimize collection and define retention for anything non-public.
  2. Map trust boundaries, owners, entry points, data stores, external services, nested repositories, and human approvals. Pay special attention to infra/.env, accounts/, the bookchaowalit-freelance/ client repositories, data/raw/, backups, and generated reports.
  3. Threat-model authentication, authorization, prompt or code injection, SSRF, unsafe file paths, webhook spoofing, excessive permissions, dependency risk, data leakage, replay, and destructive operations.
  4. Apply least privilege, allowlists, schema validation, output encoding, timeouts, rate limits, idempotency, redaction, audit events, and safe error messages.
  5. Keep secrets in approved environment or secret-management mechanisms. Never print, commit, paste into prompts, or place credentials in fixtures, logs, screenshots, or documentation.
  6. Protect client boundaries: use the client's own bookchaowalit-freelance/<client> repository, avoid cross-client data access, and do not modify nested repositories unless they are explicitly in scope.
  7. Verify with available tests, typechecks, dependency or secret scans, migration backups, and a manual review of permissions and logs. Record checks that could not run.
  8. If an incident is suspected, contain access, revoke or rotate exposed credentials, preserve relevant evidence, assess affected data, and follow the repository or client notification policy.

Stop conditions

Pause and ask for direction when the requested action needs an unapproved secret, bypasses authorization, exposes private data, sends an external message, changes production, or deletes/overwrites data without a recoverable plan.

Handoff

Report the risk, affected boundary, evidence, severity rationale, mitigation, remaining uncertainty, owner, and verification performed. Do not include the sensitive value itself.

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.