agentleFS
ElguajoElguajo/Progressive-Context-Kit/.agents/skills/security-sensitive-change/SKILL.md

security-sensitive-change

Skill0 starsChanged 42 days agoMITView on GitHub

Auth, payments, permissions, secrets, private data, untrusted input, webhooks, migrations, destructive actions, redirects, CSRF, SQL construction, or trust-boundary changes.

The file

Files
SKILL.md

Security-Sensitive Change

Apply the global High-risk approval boundary first. Verify current primary provider/framework documentation when behavior is version-sensitive. Keep privileged state server-authoritative, validate untrusted input at trust boundaries, use least privilege and secure defaults, preserve tenant isolation, and protect secrets. For retried external events/payment-like flows, preserve integrity and idempotency. Add relevant negative tests (unauthorized, malformed, replayed, cross-tenant, invalid-state) when applicable.

Refuse to implement:

  • hard-coded secrets;
  • SQL built by concatenating untrusted input;
  • disabled CSRF protection;
  • eval / exec on untrusted input;
  • unvalidated redirects.

Briefly explain the risk and provide the safe equivalent.

Require explicit confirmation for destructive/irreversible operations, production deploys, data deletion/risky migrations, breaking public APIs, auth behavior changes, major production dependencies, material scope expansion, private-data/repository transfer to external services, or creating/modifying/publishing shared/production resources. Read-only dependency metadata, package lookup, and repository fetches do not require confirmation unless private data or an unapproved service is involved.

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.