dsh-TUI: Skill for Claude Code

.agents/skills/vuln-check/SKILL.md

vuln-check is a skill for Claude Code, Codex from ccch1mneyyy/dsh-TUI. It costs 38 tokens per session (342 once invoked), scanned A, original, MIT.

A project security check for vulnerable dependencies and common code-level security problems.

In plain words
What is it for?
Use it to review lockfiles and manifests, scan source code, and receive findings with severity, evidence, and suggested fixes.
Why use it?
It helps find known-risk package versions and unsafe patterns such as command injection, path traversal, exposed secrets, and unvalidated input.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is ccch1mneyyy/dsh-TUI's own configuration. It tells Claude Code and Codex how to work on dsh-TUI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dsh-TUI configures →

About the project

dsh-TUI is a terminal interface plugin for DeepSeek Harness that gives the coding agent a Claude Code-style display with live status, streaming thoughts, rollback, context usage, and TPS information. It is for users who prefer a richer terminal workflow, and the catalogue entries extend the DeepSeek Harness environment with related skills and instructions.

ccch1mneyyy/dsh-TUI · 2,938 stars · on GitHub · dshtui.com

Reuse

Borrowing it

Nothing to install: this file belongs to ccch1mneyyy/dsh-TUI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ccch1mneyyy/dsh-TUI/main/.agents/skills/vuln-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ccch1mneyyy/dsh-TUI

Made for: Claude Code, Codex.

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 vuln-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/ccch1mneyyy/dsh-tui/vuln-check/github.svg)](https://agentmods.dev/skills/ccch1mneyyy/dsh-tui/vuln-check)
Your own site
<a href="https://agentmods.dev/skills/ccch1mneyyy/dsh-tui/vuln-check"><img src="https://agentmods.dev/badge/skills/ccch1mneyyy/dsh-tui/vuln-check/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 vuln-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/ccch1mneyyy/dsh-tui/vuln-check"><img src="https://agentmods.dev/badge/skills/ccch1mneyyy/dsh-tui/vuln-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 342 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00038 $0.00342
Opus 5 $0.00019 $0.00171
Sonnet 5 $0.00008 $0.00068
Haiku 4.5 $0.00004 $0.00034

Measured 2d ago against content hash c2a3540849e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

vuln-check 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 2d 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.

.agents/skills/vuln-check/SKILL.md · 15 lines

What it actually says

Assess the requested security surface with evidence. A check returns findings; implement remediation when the user has requested it.

  1. Read package.json and pnpm-lock.yaml for the affected dependency paths. Use current advisory data, such as pnpm audit, and record the resolved version, advisory, affected range, and verified fixed version where available. Distinguish a dependency advisory match from a demonstrated exploit path in this project.
  2. Trace untrusted inputs through guards to sensitive operations: shell execution, filesystem access, plugin capabilities, and terminal escape output. For paths, check containment and symlink behavior where relevant; normalization alone does not prevent traversal. Inspect actual validation and authorization before treating a suspicious API as a vulnerability. Scan committed repository files for potential secrets; report only the path, line, and secret type, never the value or a source excerpt.
  3. Report findings by severity with location, trigger, impact, evidence, and the smallest effective remedy. Separate confirmed issues from leads needing verification. Preserve the upstream peer/dev dependency contract when proposing upgrades.
  4. State the scope, sources checked, and gaps. If advisories are unavailable, report that the dependency check is incomplete; absence of findings is not a claim that the project is vulnerability-free.

Report potential secrets only by path, line, and type, never their value or a source excerpt. Do not run automatic dependency fixes as part of a check; for requested remediation, make targeted changes and validate the affected paths.

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. 2d ago Changed · -12 lines c2a3540849e5
  2. 11d ago First seen · 27 lines · 38 tokens per session scan A 59791aa4b269

Subscribe to this mod's changes

vuln-check is a skill published in the GitHub repository ccch1mneyyy/dsh-TUI (2,938 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 342 once invoked, about $0.0002 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 2026-08-30.