loom-security-scan

loom-security-scan is a skill for Claude Code from cosmix/loom. It costs 21 tokens per session (2,242 once invoked), scanned A, original, MIT.

A set of quick security checks for code, dependencies, container images, and infrastructure settings. Dependencies are outside software packages your project uses, while container images package software for deployment.

In plain words
What is it for?
Use it for lightweight checks before committing code or in CI, with tools for secrets, JavaScript, Python, Go, and Rust dependencies, containers, Dockerfiles, Terraform, Kubernetes, and source code.
Why use it?
It catches exposed secrets, known security flaws, and common configuration problems before they reach a commit or continuous integration (CI) build.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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 skills/cosmix/loom/loom-security-scan
Any agent
npx skills add cosmix/loom --skill loom-security-scan
Clone the repo
git clone --depth 1 https://github.com/cosmix/loom

Made for: Claude Code.

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 loom-security-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/cosmix/loom/loom-security-scan.svg)](https://agentmods.dev/skills/cosmix/loom/loom-security-scan)
Your own site
<a href="https://agentmods.dev/skills/cosmix/loom/loom-security-scan"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-security-scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,242 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.02242
Opus 5 $0.00010 $0.01121
Sonnet 5 $0.00004 $0.00448
Haiku 4.5 $0.00002 $0.00224

Measured 2d ago against content hash 8304de346463, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

loom-security-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 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.

skills/loom-security-scan/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Scan

Fast, automatable checks to run pre-commit / in CI — catch secrets, known-CVE deps, image and IaC misconfig early. This is the tooling skill; for methodology and compliance use loom-security-audit, for STRIDE use loom-threat-model, for deep dependency/SBOM work use loom-dependency-scan.

Tool Selection Matrix

Scan type Tool Alternative Notes
Secrets TruffleHog Gitleaks TruffleHog verifies live creds; Gitleaks is regex-fast
Deps (JS) npm audit osv-scanner, Snyk --audit-level=high
Deps (Python) pip-audit safety pip-audit uses OSV/PyPI advisory DB
Deps (Go) govulncheck osv-scanner call-graph aware → fewer false positives
Deps (Rust) cargo audit cargo-deny RustSec DB
Container image Trivy Grype --scanners vuln,secret,config
SAST multi-lang Semgrep CodeQL p/security-audit, p/secrets
SAST Python Bandit Semgrep
SAST Go gosec Semgrep
Dockerfile hadolint Trivy config best-practice lint
IaC (Terraform) tfsec / trivy config Checkov
IaC (K8s) kubesec / trivy Checkov
Universal (fs+img, vuln+secret+config) Trivy osv-scanner one binary for most CI needs

Priority Order

Run cheapest/highest-signal first; a secret in git history is worse than a medium CVE.

1. Secrets (Critical)

Prefer dedicated tools over grep — they cut false positives and TruffleHog verifies whether a key is live.

trufflehog filesystem . --only-verified --no-update   # only credentials confirmed active
gitleaks detect --source . --redact                   # scans full git HISTORY by default

⚠ Secret-scanning gotchas:

  • Scan history, not just the worktree. A rotated key still lives in old commits and forks. gitleaks detect walks history; gitleaks detect --no-git / trufflehog filesystem only see current files. A committed-then-deleted secret must be rotated, not just removed — deletion doesn't scrub history.
  • --only-verified (TruffleHog) suppresses unverifiable/expired hits — great for CI signal, but it will miss a secret whose endpoint it can't reach; run a full pass periodically.
  • Regex fallback for a quick look (dedicated tools are better): AWS keys (AKIA|ASIA)[A-Z0-9]{16}, PEM -----BEGIN (RSA |EC |OPENSSH )?PRIVATE KEY-----, generic (password|secret|token|api[_-]?key)\s*[:=]\s*['"][^'"]{8,}.

Read the full file on GitHub · 188 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. 2d ago Changed · -46 tokens per session 8304de346463
  2. 6d ago First seen · 188 lines · 67 tokens per session scan A b3c1bd6132f2

Subscribe to this mod's changes

loom-security-scan is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 2,242 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

workers-best-practices

Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from…

cloudflare/skills · 72 tokens

find-journalists

Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.

elvisun/newsjack · 69 tokens

story-origin-check

Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.

elvisun/newsjack · 40 tokens

annotating-task-lineage

Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.

astronomer/agents · 51 tokens

ai-visibility-writing

Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…

elvisun/newsjack · 137 tokens

aws-cloudformation-cloudfront

Provides AWS CloudFormation patterns for CloudFront distributions, origins (ALB, S3, Lambda@Edge, VPC Origins), CacheBehaviors, Functions, SecurityHeaders, parameters, Outputs and cross-stack references. Use when creating CloudFront distributions with CloudFormation, configuring multiple origins, implementing caching…

giuseppe-trisciuoglio/developer-kit · 81 tokens