loom-security-audit

loom-security-audit is a skill for Claude Code from cosmix/loom. It costs 20 tokens per session (2,568 once invoked), scanned B, original, MIT.

A detailed security review of applications, APIs, infrastructure, and data pipelines. It looks for vulnerabilities, unsafe settings, and violations of security best practices.

In plain words
What is it for?
Use it for OWASP reviews, compliance assessments such as SOC 2, PCI DSS, HIPAA, or GDPR, threat and risk reviews, and security hardening.
Why use it?
It finds deeper problems that quick automated scans may miss, ranks their severity, and ties findings to evidence and specific fixes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is open(os.path.join(base, filename)) # ✗ filename="../../etc/passwd".

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/cosmix/loom/loom-security-audit.svg)](https://agentmods.dev/skills/cosmix/loom/loom-security-audit)
Your own site
<a href="https://agentmods.dev/skills/cosmix/loom/loom-security-audit"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-security-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,568 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 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 $0.00020 $0.02568
Opus 5 $0.00010 $0.01284
Sonnet 5 $0.00004 $0.00514
Haiku 4.5 $0.00002 $0.00257

Measured 2d ago against content hash f65a0213bccf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

loom-security-audit scanned grade B with 3 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.

Cloud metadata endpointmediumServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

Any server-side fetch of a user-influenced URL (webhooks, image proxies, PDF renderers, URL previews, importers) can be pointed at internal services or the cloud metadata endpoint `169.254.169.254` to steal IAM credentia

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

fetch(url, allow_redirects=False, timeout=5)

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

os.system(f"ping {host}") # ✗
skills/loom-security-audit/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Audit

Deep, methodical security review producing evidenced, severity-ranked, remediable findings — the heavyweight companion to loom-security-scan (fast tooling). Delegates: STRIDE/architecture → loom-threat-model; authn/authz mechanisms → loom-auth; dependency/SBOM/supply-chain → loom-dependency-scan.

Method

  1. Scope — assets, data classification, compliance obligations, threat model (pull from loom-threat-model). Define what "in scope" means before touching anything.
  2. Review by layer — app code, APIs, infra/IaC, data pipelines, ML (sections below).
  3. Evidence — every finding cites file:line or config path + a concrete exploit scenario. A finding without a repro is a guess.
  4. Rate — CVSS or Likelihood×Impact; rank most-severe first.
  5. Remediate — specific fix (ideally a diff), not "sanitize inputs".
  6. Report — executive summary + technical detail + prioritized remediation.

Run tooling first (loom-security-scan) to clear known-pattern noise, then spend human effort on logic and authorization flaws that scanners miss — that's where audits earn their keep.

OWASP Top 10 (2021) — audit lens

# Category First things to check
A01 Broken Access Control IDOR/BOLA, missing function-level authz, path traversal, CORS, force-browsing. Most common; start here.loom-auth
A02 Cryptographic Failures Plaintext/weak-hash secrets, TLS < 1.2, weak ciphers, hardcoded keys, ECB mode
A03 Injection SQL/NoSQL/command/LDAP/XPath, XSS, ORM raw queries
A04 Insecure Design Missing threat model, no rate limiting by design, trust assumptions
A05 Security Misconfiguration Default creds, verbose errors, open cloud storage, missing headers, debug on
A06 Vulnerable Components Outdated deps with CVEs → loom-dependency-scan
A07 Identification & Auth Failures Weak passwords, no MFA, session fixation, credential stuffing → loom-auth
A08 Software & Data Integrity Unsigned artifacts, insecure deserialization, CI/CD supply chain
A09 Logging & Monitoring Failures No audit trail, secrets in logs, no alerting, tamperable logs
A10 SSRF Server fetches attacker-controlled URLs → internal/metadata (see below)

Read the full file on GitHub · 178 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 f65a0213bccf
  2. 6d ago First seen · 178 lines · 66 tokens per session scan B c4a1885257ca

Subscribe to this mod's changes

loom-security-audit is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 2,568 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 3 findings (cloud metadata endpoint, makes network calls, runs shell commands). 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