agentleFS
Sign inStart free
emb715emb715/neurodiveragents/skills/ndv-vigilant/SKILL.md

ndv-vigilant

Skill2 starsChanged 2 months agoMITView on GitHub

Security-aware cognitive module. Injects threat-detection thinking into any phase that handles user input, auth flows, data access, or trust boundaries. Source: ndv-secure (Ward).

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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. Distinctive:

    Every "probably secure" is an assumption someone made without testing it.

    line 16
  2. Distinctive:

    Check auth on every protected operation — never assume the caller is authorized

    line 24
  3. Distinctive:

    No secrets in code, logs, or error messages

    line 25
  4. Distinctive:

    Use parameterized queries — never string concatenation for data access

    line 26
  5. Distinctive:

    Use cryptographically secure randomness for tokens and secrets

    line 29
  6. Very specific:

    Use Math.random() for security-sensitive values

    line 35

≈ “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

The threat-detection system never turns off. Every input is a potential weapon. Every trust boundary is a liability until proven otherwise. Every "probably secure" is an assumption someone made without testing it.

Primordial rule: Trust no input. Assume breach. Every user-provided value is hostile until validated server-side. Client-side validation is UX, not security.

Constraints:

  • Validate all input server-side — type, format, bounds, authorization
  • Check auth on every protected operation — never assume the caller is authorized
  • No secrets in code, logs, or error messages
  • Use parameterized queries — never string concatenation for data access
  • Least privilege — grant minimum necessary access
  • Log auth failures and suspicious patterns, never log sensitive data
  • Use cryptographically secure randomness for tokens and secrets

Never:

  • Trust client-side validation as sufficient
  • Accept "probably secure" without testing
  • Log sensitive data (passwords, tokens, PII)
  • Use Math.random() for security-sensitive values
  • Hardcode secrets or credentials
  • Miss auth checks on endpoints that modify data

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