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 agentmods add skills/cosmix/loom/loom-dependency-scannpx skills add cosmix/loom --skill loom-dependency-scangit clone --depth 1 https://github.com/cosmix/loomWrote 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/cosmix/loom/loom-dependency-scan)<a href="https://agentmods.dev/skills/cosmix/loom/loom-dependency-scan"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-dependency-scan.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00035 | $0.01670 |
| Opus 5 | $0.00017 | $0.00835 |
| Sonnet 5 | $0.00007 | $0.00334 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade B, and why
loom-dependency-scan scanned grade B with 1 finding 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- **Malicious install scripts** — npm `postinstall`, pip `setup.py` run arbitrary code at install. Use `npm ci --ignore-scripts` where feasible; audit scripts of new deps. How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Scan
CVEs, outdated packages, license compliance, and supply-chain risk across ecosystems. Deep-dependency companion to loom-security-scan (fast pre-commit/CI scanning) and loom-security-audit (methodology/compliance).
Workflow
- Enumerate — parse manifests + lockfiles; separate direct vs transitive. No lockfile → builds aren't reproducible (fix first).
- Scan — CVEs against advisory DBs (below); note severity, affected/fixed versions, and the dependency path.
- Assess reachability — a CVE in an unimported/dev-only path is lower priority than one on a hot code path.
govulncheckand Snyk reason about reachability;npm auditdoes not. - Remediate — minimal safe bump to the fixed version; prefer patch/minor; verify tests. Pin the result in the lockfile.
Scanning Commands
# JS npm audit --audit-level=high | osv-scanner -r .
# Python pip-audit | safety check
# Rust cargo audit | cargo deny check advisories
# Go govulncheck ./... | go list -m all | nancy sleuth
# Ruby bundle audit --update
# Java mvn org.owasp:dependency-check-maven:check
# .NET dotnet list package --vulnerable --include-transitive
# PHP composer audit
# Any osv-scanner -r . (lockfile-driven, OSV DB, all major ecosystems in one)
⚠ --vulnerable/audit tools only see what the lockfile pins — an unpinned range (^1.2.0) may resolve differently in CI. Scan the committed lockfile, and regenerate it before scanning if manifests changed.
Supply-Chain Attacks (the high-signal risks)
Registry malware now outpaces classic CVEs. Defenses are structural, not just "run audit":
- Dependency confusion — you have an internal package
@acme/utils; an attacker publishes@acme/utilsto the public registry with a higher version. A misconfigured resolver prefers the public one and runs attacker code at install. Defend: scope internal packages to your private registry, configure the client to never fall back to public for those scopes (npm.npmrc@acme:registry=…, pip--index-urlnot--extra-index-url), and claim/reserve your names on the public registry. - Typosquatting —
reqeusts,lodahs,python-dateutilvsdateutil. Review every new dependency name character-by-character; watch install-time scripts. Prefer well-known packages with history and many maintainers. - Namespace / maintainer hijack — a legit package gets a malicious release after an account takeover or a maintainer handoff. Defend: pin exact versions + lockfile hash integrity; delay auto-adopting brand-new releases (Renovate
stabilityDays); watch for sudden maintainer changes. - Malicious install scripts — npm
postinstall, pipsetup.pyrun arbitrary code at install. Usenpm ci --ignore-scriptswhere feasible; audit scripts of new deps. - Integrity — commit lockfiles with hashes (
package-lock.json,Cargo.lock,poetry.lock,pip-compile --generate-hashes). Hashes turn a hijacked re-publish of an existing version into a hard install failure.
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.
- 2d ago Changed · -18 tokens per session e070cb5ac6c8
- 6d ago First seen · 126 lines · 53 tokens per session scan B df832bda72cb
loom-dependency-scan is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,670 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…
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.
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.
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.
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…
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…