agentleFS
Sign inStart free
mcabreradevmcabreradev/hermes-sdd-agency/skills/security-evidence-first/SKILL.md

security-evidence-first

Skill1 starsChanged 57 days agoMITView on GitHub

Security review: evidence before assurance; attacker, boundary, impact, challenge.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Distinctive:

    Check the OWASP categories that apply to the stack (injection, broken access control, secrets, insecure deserialization, SSRF… — adapt to …

    line 26

≈ “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
<!-- hermes-add-skill: framing adapted from gstack /cso (garrytan/gstack, MIT). Only the review discipline is kept; the heavy runtime (Docker/catalogs) is out of scope for this agency. -->

Security review: evidence before assurance

Find exploitable defects, and prove each one — not "we ran a scanner". Every finding is stated with attacker, boundary, impact, and challenge.

The four-part finding

PartWhat it forces
AttackerWho is the actor and what can they already do? (anonymous, authenticated low-priv, internal, LLM-fed input…)
BoundaryWhere does trust cross? What is trusted input vs untrusted input at this seam?
ImpactWhat breaks or is exposed if exploited — confidentiality/integrity/availability, and who sees the cost?
ChallengeWhat's the strongest honest objection to calling this exploitable? Say it yourself.

A finding missing any of the four is not actionable and goes back.

OWASP-informed scope

Check the OWASP categories that apply to the stack (injection, broken access control, secrets, insecure deserialization, SSRF… — adapt to what the project is). Report only what the project could actually exhibit; a boilerplate OWASP list with no evidence is noise.

Rules

  • Evidence before assurance: a claim of security needs the reproduction path, not a vibe. "We reviewed for X" without a concrete finding + evidence is blocked, not pass.
  • --diff mental model: prioritize the branch/worktree change and its affected security paths over re-auditing the whole untouched surface.
  • Containment / no host blast radius is the operator's job, not a claim to make inside the review. Do not assert sandboxing you didn't set up.
  • Findings, evidence, and harnesses are not uploaded anywhere or sent to any remote — they live in the report.

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