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.
npx skills add softspark/ai-toolkit --skill cve-scangit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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.
[](https://agentmods.dev/skills/softspark/ai-toolkit/cve-scan)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/cve-scan"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/cve-scan/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.
<a href="https://agentmods.dev/skills/softspark/ai-toolkit/cve-scan"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/cve-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.01454 |
| Opus 5.5 | $0.00019 | $0.00582 |
| Sonnet 5.5 | $0.00009 | $0.00291 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade A, and why
cve-scan 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cve-scan - Dependency CVE Scanner
$ARGUMENTS
Detect project ecosystems and scan dependencies for known vulnerabilities using native audit tools. Zero external dependencies — uses tools already installed in the project environment.
Usage
/cve-scan # Auto-detect all ecosystems, scan all
/cve-scan --ecosystem npm # Force specific ecosystem
/cve-scan --fix # Auto-fix where possible (npm audit fix, etc.)
/cve-scan --json # Machine-readable JSON output
What This Command Does
- Detect package managers by lock/manifest files in the project
- Run the native audit command for each detected ecosystem
- Parse results into a unified severity-based report
- Report CVE IDs, affected packages, installed vs fixed versions, advisory links
- Fix automatically when
--fixis passed (where the tool supports it)
Ecosystem Detection & Commands
| Manifest File | Lock File | Ecosystem | Audit Command | CVE Database |
|---|---|---|---|---|
package.json |
package-lock.json / yarn.lock / pnpm-lock.yaml |
npm/yarn/pnpm | npm audit --json / yarn audit --json / pnpm audit --json |
GitHub Advisory DB |
requirements.txt / pyproject.toml / setup.py |
requirements.txt |
pip | pip-audit --format=json |
OSV / PyPI Advisory |
composer.json |
composer.lock |
composer | composer audit --format=json |
Packagist / FriendsOfPHP |
Cargo.toml |
Cargo.lock |
cargo | cargo audit --json |
RustSec Advisory DB |
go.mod |
go.sum |
go | govulncheck ./... |
Go Vulnerability DB |
Gemfile |
Gemfile.lock |
bundler | bundle-audit check |
Ruby Advisory DB |
pubspec.yaml |
pubspec.lock |
dart/flutter | dart pub outdated --json |
pub.dev |
Steps
- Detect ecosystems: Glob for manifest/lock files at project root and common subdirectories
- Check tool availability: Verify audit tool is installed for each detected ecosystem
- Run audit: Execute native audit command, capture JSON output where available
- Parse results: Extract CVE ID, package name, installed version, fixed version, severity, advisory URL
- Unified report: Merge all ecosystems into single report sorted by severity
- Fix mode: If
--fixpassed, runnpm audit fix,pip-audit --fix,cargo audit fixetc. - Exit code: Non-zero if any CRITICAL or HIGH vulnerabilities found
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 135 lines · 47 tokens per session scan A 3b8e1c52fb95
cve-scan is a skill published in the GitHub repository softspark/ai-toolkit (180 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 1,454 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
cline-fix-volatile-msg
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
continue-gemini-explicit
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.
roo-fix-volatile-msg
Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).
aider-1h-ttl
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
cline-openai-cache-key
Cline OpenAI native provider sends no promptcachekey. Add a stable per-task key so cachedtokens stops being zero.
continue-enable-defaults
Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.