agentmods.dev

triaging-vulnerable-dependencies

triaging-vulnerable-dependencies is a skill for Claude Code from gnana997/bumper. It costs 91 tokens per session (660 once invoked), scanned A, original, Apache-2.0.

A dependency-safety workflow that scans lockfiles for known security flaws and packages identified as malicious. A lockfile records the exact dependency versions a project installs.

In plain words
What is it for?
Use it when adding or upgrading packages or editing files such as `package-lock.json` and `yarn.lock` to review findings and choose a safer version.
Why use it?
It helps prevent a project from installing a vulnerable or harmful package during dependency changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the bumper plugin — 3 skills shipped together

not rated 2repo 16d ago A scan 91 tokens original Apache-2.0

Good fit Use it when adding or upgrading packages or editing files such as package-lock.json and yarn.lock to review findings and choose a safer version.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gnana997/bumper/triaging-vulnerable-dependencies
View source ↗ gnana997/bumper bumper.sh
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add gnana997/bumper --skill triaging-vulnerable-dependencies
Clone the repo
git clone --depth 1 https://github.com/gnana997/bumper

Made for: Claude Code.

Or install bumper, the plugin that ships this one along with the rest of its 3 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for triaging-vulnerable-dependencies

README.md
[![agentmods](https://agentmods.dev/badge/skills/gnana997/bumper/triaging-vulnerable-dependencies/github.svg)](https://agentmods.dev/skills/gnana997/bumper/triaging-vulnerable-dependencies)
Your own site
<a href="https://agentmods.dev/skills/gnana997/bumper/triaging-vulnerable-dependencies"><img src="https://agentmods.dev/badge/skills/gnana997/bumper/triaging-vulnerable-dependencies/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for triaging-vulnerable-dependencies

Your own site · 80×15
<a href="https://agentmods.dev/skills/gnana997/bumper/triaging-vulnerable-dependencies"><img src="https://agentmods.dev/badge/skills/gnana997/bumper/triaging-vulnerable-dependencies.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 660 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.00660
Opus 5 $0.00046 $0.00330
Sonnet 5 $0.00018 $0.00132
Haiku 4.5 $0.00009 $0.00066

Measured 9d ago against content hash b9ec46f693a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

triaging-vulnerable-dependencies scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

internal/skills/content/triaging-vulnerable-dependencies/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triaging vulnerable dependencies with bumper

bumper scans dependencies for known vulnerabilities and known-malicious packages, using the bumper Advisor for data. It needs the bumper CLI on PATH (https://github.com/gnana997/bumper). If a package is flagged malicious, do not install it.

Workflow

  1. Scan the lockfile(s):

    bumper deps                       # auto-detect lockfiles in the current directory
bumper deps --json path/to/lock   # machine-readable findings for one file

    Exit codes: 0 = clean, 1 = findings present, 2 = usage error.

  2. For each finding, get authoritative detail. Prefer the bumper-advisor MCP when connected (use fully-qualified tool names):

    • bumper-advisor:lookup_cve — CVEs affecting a specific package + version (args: ecosystem, package, version)
    • bumper-advisor:get_vuln — full detail for one advisory id (CVE/GHSA)
    • bumper-advisor:check_malware — reputation of a package (is it malware?)
    • bumper-advisor:search_cve — search CVEs by keyword/ecosystem

    If the MCP is not connected, fall back to the CLI: bumper deps --json ….

  3. Decide per finding:

    • Malicious package → do NOT install. Remove it; find a trusted alternative.
    • Vulnerable, fix available → upgrade to the lowest version that clears the advisory (lookup_cve / get_vuln list fixed versions).
    • Vulnerable, no fix → surface the risk to the user; pin and isolate, or drop the dependency. Do not silently proceed.

  4. Apply the fix and re-scan (repeat until clean): a. Update the manifest/lockfile to the chosen version. b. bumper deps. c. If findings remain, return to (a).

Example

Adding lodash:

  1. bumper deps → HIGH: lodash 4.17.4 (prototype pollution).
  2. bumper-advisor:lookup_cve ecosystem=npm package=lodash version=4.17.4 → fixed in 4.17.12.
  3. Bump to lodash ^4.17.21, re-run bumper deps → clean. Install.

Full, version-matched procedure

For the complete steps and any checks specific to this installed bumper version:

bumper skills get deps-triage

Read the full file on GitHub · 58 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 58 lines · 91 tokens per session scan A b9ec46f693a1

Subscribe to this mod's changes

triaging-vulnerable-dependencies is a skill published in the GitHub repository gnana997/bumper (2 stars, last pushed 16d ago), licensed Apache-2.0. It adds 91 tokens to every session and 660 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeSecurityclicontinuous-integrationdependency-scanningdevsecopsgemini-cli
Related

Other skills, from other repositories

ccmanager-config

Set up, review, or repair a CCManager config — .ccmanager.json at a git repository root, or the global /.config/ccmanager/config.json. Use when someone wants ccmanager to launch a different agent CLI (codex, gemini, cursor-agent, copilot…), add command presets, run a command on session state changes or worktree…

kbwo/ccmanager · 123 tokens

performing-sca-dependency-scanning-with-snyk

This skill covers implementing Software Composition Analysis (SCA) using Snyk to detect vulnerable open-source dependencies in CI/CD pipelines. It addresses scanning package manifests and lockfiles, automated fix pull request generation, license compliance checking, continuous monitoring of deployed applications, and…

xalgorix/xalgorix · 77 tokens

microsoft-typescript

TypeScript is a language for application scale JavaScript development. ALWAYS use when editing or working with .ts, .tsx, .mts, .cts files or code importing "typescript". Consult for debugging, best practices, or modifying typescript, TypeScript.

skilld-dev/skilld · 57 tokens

sindresorhus-log-update

Log by overwriting the previous output in the terminal. Useful for rendering progress bars, animations, etc. ALWAYS use when writing code importing "log-update". Consult for debugging, best practices, or modifying log-update, log update.

skilld-dev/skilld · 54 tokens

performing-sca-dependency-scanning-with-snyk

This skill covers implementing Software Composition Analysis (SCA) using Snyk to detect vulnerable open-source dependencies in CI/CD pipelines. It addresses scanning package manifests and lockfiles, automated fix pull request generation, license compliance checking, continuous monitoring of deployed applications, and…

adriannoes/awesome-agentic-ai · 77 tokens

jfrog

Interact with the JFrog Platform via the JFrog CLI, JFrog MCP server and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search…

jfrog/jfrog-skills · 204 tokens