verify-dependency-vulnerability

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.

agentmods

npx agentmods add commands/morpho-org/sdks/verify-dependency-vulnerability

Clone the repo

git clone --depth 1 https://github.com/morpho-org/sdks

Made for: Codex.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,388 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.02388
Opus 5	$0.00000	$0.01194
Sonnet 5	$0.00000	$0.00478
Haiku 4.5	$0.00000	$0.00239

Measured yesterday against content hash d8cc5c69aae1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-dependency-vulnerability 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 yesterday.

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/commands/verify-dependency-vulnerability.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify if this codebase is affected by a dependency vulnerability (CVE, supply chain attack, compromised package, etc.).

Usage

/verify-dependency-vulnerability <CVE | advisory URL | package@version description>

Required Input

The user must provide:

A CVE identifier (e.g., CVE-2025-55182)
A URL to a security advisory, blog post, changelog, or any document containing vulnerability details
A description of a supply chain attack or compromised package

Step 1: Gather Vulnerability Details

1a: Attempt to Fetch Vulnerability Information

If the user provided a URL or CVE identifier:

Use WebFetch to retrieve the document
If the fetch succeeds, extract:
- Affected packages: List all package names affected by this vulnerability
- Compromised versions: The exact version ranges that are vulnerable or compromised
- Safe versions: The EXACT list of safe/patched versions (not ranges)

1b: Handle Inaccessible Sources

If WebFetch fails for ANY reason, you MUST use AskUserQuestion to prompt the user:

The vulnerability source at [URL] could not be accessed or parsed.

Please provide the vulnerability details manually:
- Package names affected
- Safe versions for each package (list ALL safe versions, e.g., "15.0.5, 15.1.9, 15.2.6")

DO NOT proceed without this information. DO NOT guess or assume versions.

1c: Validate Extracted Information

After fetching or receiving manual input, confirm you have:

At least one affected package name
The specific safe versions (not just "upgrade to latest")

If the source only says "upgrade to latest" without specific versions, ask the user to provide the exact safe version numbers or check the package's GitHub releases/changelog.

Step 2: Understand the Safe Versions Structure

CRITICAL: Pay attention to how safe versions are listed. Many vulnerabilities are patched separately for each minor version line. For example:

15.0.5, 15.1.9, 15.2.6, 15.3.6, 15.4.8, 15.5.7 means:
- 15.0.x line: only 15.0.5+ is safe
- 15.1.x line: only 15.1.9+ is safe
- 15.5.x line: only 15.5.7+ is safe
- Version 15.5.5 is COMPROMISED even though 15.0.5 is safe

Read the full file on GitHub · 275 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.

yesterday First seen · 275 lines · 0 tokens per session scan A d8cc5c69aae1

Subscribe to this mod's changes