agentsclimarketplace

Route security work

Skill gaelic-ghost/socket/plugins/cybersecurity-skills/skills/route-security-work

The Source for macOS Agent Workflows

Install
npx -y skills add gaelic-ghost/socket --skill route-security-work

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

One thing to look at

  • 6 stars6 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

Route an ambiguous cybersecurity request before tools run. Use for suspicious files, links, messages, host behavior, malware, vulnerability reports, authorized pentests, incidents, threat hunting, detection work, or security advice.

SKILL.md

2.5 KB, 447 tokens by cl100k_base, as published. Nobody here has run it

Route Security Work

Overview

Turn the user's concern into one bounded security question, identify the affected surface, and select the smallest safe owner workflow. Do not begin active probing or execute suspicious content during routing.

Read references/routing-map.md when ownership or the difference between investigation, testing, response, and remediation is unclear.

Workflow

  1. State the requested decision.

    • Capture what the user needs to know or do now.
    • Separate “is this dangerous?” from “how does it work?”, “am I affected?”, and “how do I fix it?”.

  2. Identify the surface.

    • Classify the primary subject as content or artifact, endpoint, identity, network/service, application/source, vulnerability report, or active incident.
    • Record the relevant artifact, host, account, service, repository, target, and time window.

  3. Establish authority and urgency.

    • For inspection and defensive response, confirm the user controls or is responsible for the affected surface.
    • Before active testing, require the target owner, allowed targets, exclusions, time window, techniques, stop conditions, and contacts.
    • If harm is ongoing, route immediate containment separately from evidence preservation.

  4. Choose the next owner.

    • Use preserve-security-evidence before transformations or volatile state disappears.
    • Use select-analysis-isolation before opening or executing untrusted content.
    • Use assess-and-explain-threat when evidence exists but the practical conclusion is unclear.
    • Route deep binary work to reverse-engineering-skills and repository-wide source scans to Codex Security when available.
    • Route ordinary implementation or remediation to the owning Apple, protocol, language, or framework skill after the security acceptance criteria are explicit.

  5. Report the route.

    • Name the selected workflow, why it fits, what is intentionally deferred, and the first non-destructive action.
    • Preserve uncertainty rather than selecting a dramatic path from weak evidence.

Output

Return the security question, affected surface, urgency, authority/scope state, selected owner, first safe action, and any immediate stop condition.

What ships with it: 2 files

1.5 KB alongside SKILL.md

agents/

references/

Gives 0 of the 12 instructions most security skills give in 447 tokens

Counted across 648 of the 828 authors here whose files we hold, read 2026-08-07

  • Parameterize all database queriesin 68 of 648, across 51 files
  • Hash passwords using bcrypt, scrypt, or argon2in 49 of 648, across 36 files
  • Apply rate limiting to authentication endpointsin 48 of 648, across 24 files
  • Configure security headersin 35 of 648, across 19 files
  • Validate all inputsin 32 of 648, across 24 files
  • Validate all external input at the system boundaryin 29 of 648, across 19 files
  • Run containers as a non-root userin 28 of 648, across 15 files
  • Use httponly secure samesite cookies for sessionsin 26 of 648, across 15 files
  • Run dependency audits before every releasein 21 of 648, across 10 files
  • Encode output to prevent cross-site scriptingin 21 of 648, across 11 files
  • Copy dependencies before source codein 20 of 648, across 9 files
  • Store secrets in environment variablesin 20 of 648, across 18 files

Said here and by no other author read

  • state the requested decision
  • identify the affected surface
  • establish authority and urgency
  • choose the next owner workflow
  • report the selected route
  • confirm user controls the affected surface

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 327,069. 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.