agentleFS
mgkvibezmgkvibez/sentinel-skills/skills/cve-research/SKILL.md

cve-research

Skill2 starsChanged 18 days agoMITView on GitHub

Research a CVE and decide exposure for a specific codebase. Use when given a CVE identifier and asked whether we are affected, what it does, or how to remediate.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. ashrafiucse/security-audit-skills★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Never cite a version range you have not read from a primary source.

    line 50
  2. Distinctive:

    If exploit details are needed for defence, describe the mechanism, not a working exploit.

    line 52
  3. Distinctive:

    Do not invent CVSS scores.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

CVE research

Answer three questions in order: what it does, are we exposed, what do we do now.

When to use

  • A CVE identifier is mentioned and someone asks "are we affected".
  • A dependency alert carries a CVE that needs explanation.

Procedure

  1. Establish the facts from primary sources: the CVE record, the vendor advisory, the fix commit, and the affected version ranges. Prefer the fix commit over blog summaries. Done when: affected ranges are quoted exactly from a primary source.
  2. Determine the vulnerable code path. Name the function that contains the flaw and what an attacker gains by reaching it. If the advisory does not say, read the fix commit. Done when: the vulnerable function is named and the attacker gain is stated.
  3. Check local exposure. Resolve the installed version from the lockfile, then search for imports and call sites of the vulnerable function. Done when: resolved version and call sites are recorded, or "not imported" with evidence.
  4. Assess exploitability in this deployment: exposed surface, authentication requirement, configuration preconditions (for example debug mode or a specific backend). Done when: preconditions are checked against actual configuration files, not assumed.
  5. Give the remediation: upgrade target version, backport availability, mitigation if upgrade is blocked, and a way to verify the fix landed. Done when: a verification command is included.

Output format

## CVE summary
id:  component:  published:  cvss:
## Affected ranges (primary source)
## Vulnerable path
function:  attacker gain:
## Local exposure
resolved:  imported:  call sites:  evidence:
## Exploitability here
## Remediation
upgrade to:  mitigation:  verify with:

Rules

  • Never cite a version range you have not read from a primary source.
  • Distinguish "vulnerable code present" from "exploitable in this deployment".
  • If exploit details are needed for defence, describe the mechanism, not a working exploit.
  • Do not invent CVSS scores. Quote published ones and state your own assessment separately.

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.