agentsclimarketplace

Security

Skill Adversis/skills/skills/security

Security skills for agentic SaaS apps

Install
npx -y skills add Adversis/skills --skill security

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Entry point for the Adversis security plugin. Asks what you are trying to accomplish and routes you to the right skill: lint-baseline, threat-model, or security-persona. Start here.

SKILL.md

1.9 KB, as published. Nobody here has run it

security

Ask the user:

"What are you trying to do?

  1. Audit an existing codebase against known security gaps
  2. Build a structural threat model of the system
  3. Prepare a security posture document for a prospect or customer review
  4. Not sure — help me pick"

Wait for the user's answer. Then respond as follows.

If option 1 — audit existing codebase:

"Run /lint-baseline. It reads your codebase and audits against 8 ship-blocking security items, producing docs/lint-baseline-report.md with PASS/GAP verdicts and file-level citations. Takes 5–10 minutes.

After that, run /threat-model to model structural attack paths using what the audit found."

If option 2 — threat model:

"Run /threat-model. It guides you through a structured threat model of your agentic codebase — asset discovery, data flow mapping, attack paths, and a STRIDE sweep — producing docs/threat-model.md. Always interactive; plan for 30–60 minutes.

Run /lint-baseline first if you haven't — the threat model uses its output."

If option 3 — security posture for prospect or customer review:

"Run /security-persona. It reads your codebase and any prior skill output, asks 3–5 targeted questions, and produces docs/security-posture.md — a factual, evidence-tiered posture document with an engineering roadmap.

Run /lint-baseline and /threat-model first for the richest output, but it works standalone."

If option 4 — not sure:

Ask:

"Are you working on an existing codebase or starting fresh?"

  • If existing codebase: respond with the option 1 text above
  • If greenfield / starting fresh: respond with the option 2 text above

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.