get-github-advisories
Skill0 starsChanged 9 months agoApache-2.0View on GitHub
Query the GitHub Advisory Database for vulnerabilities affecting a package in a specific ecosystem, optionally narrowed by version and severity.
In this repository21 other files it gives its agents.
- accept-prSkill
- approve-with-suggestionsSkill
- check-deprecated-dependenciesSkill
- get-commit-diffsSkill
- get-file-contentSkill
- get-multiple-filesSkill
- get-pr-changed-filesSkill
- get-pr-changesSkill
- get-pr-dependency-advisoriesSkill
- get-pr-detailsSkill
- get-pr-diff-line-mapperSkill
- get-pr-iterationsSkill
- get-pr-review-bundleSkill
- get-pr-threadsSkill
- list-projectsSkill
- list-repositoriesSkill
- post-pr-commentSkill
- reject-prSkill
- reset-feedbackSkill
- update-pr-threadSkill
- wait-for-authorSkill
The file
Files
Get GitHub Advisories
Platform Note
- Clean-install path: use the Go command from
.github/tools/skills-go.
Authentication
Set GH_SEC_PAT to a GitHub Personal Access Token.
- Fine-grained PATs work and do not require extra permissions for this endpoint.
- Public unauthenticated calls are possible, but this skill intentionally requires
GH_SEC_PATto avoid stricter anonymous rate limits.
Arguments
| # | Name | Required | Description |
| 1 | ecosystem | Yes | Package ecosystem (npm, pip, maven, nuget, go, rust, etc.) |
| 2 | package | Yes | Package name in the selected ecosystem |
| 3 | version | No | Package version to check (affects=package@version) |
| 4 | severity | No | Advisory severity filter (low, medium, high, critical, unknown) |
| 5 | per_page | No | Max advisories to return (1..100, default: 30) |
Examples
go run ./.github/tools/skills-go/cmd/skills-go get-github-advisories npm lodash 4.17.20 high 20Output
Returns a JSON array of advisory objects from https://api.github.com/advisories, including fields like ghsa_id, cve_id, severity, summary, and vulnerabilities.
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
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.

