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 cognitedata/builder-skills --skill securitygit clone --depth 1 https://github.com/cognitedata/builder-skillsWrote 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/cognitedata/builder-skills/security)<a href="https://agentmods.dev/skills/cognitedata/builder-skills/security"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/security/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/cognitedata/builder-skills/security"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Output Handling · line 117 Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.Fix: Validate and sanitize all model output before using it in downstream contexts. Use parameterized queries for SQL, shell quoting for commands, and HTML encoding for web output.
- high Output Handling · line 120 Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.Fix: Validate and sanitize all model output before using it in downstream contexts. Use parameterized queries for SQL, shell quoting for commands, and HTML encoding for web output.
- medium Tool Misuse · line 3 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 | $0.00119 | $0.02860 |
| Opus 5.5 | $0.00048 | $0.01144 |
| Sonnet 5.5 | $0.00024 | $0.00572 |
| Haiku 4.5 | $0.00012 | $0.00286 |
Grade A, and why
security 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 2mo 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Fix
Find and fix security issues in $ARGUMENTS (or the whole app if no argument is given). Work through every step below in order. Every step that finds an issue must also fix it.
Step 1 — Map the attack surface
Read these files before checking anything:
src/main.tsx/src/App.tsx— entry point, routing, auth gatingvite.config.ts— dev server proxy, CORS, headerspackage.json— list of third-party dependencies- Any file matching
**/auth*,**/login*,**/token*,**/credential*
Identify:
- All pages/routes and whether each is behind an auth guard
- All places where external data enters the app (CDF SDK calls,
fetch, user form input) - All places where data is written back (CDF upsert,
fetchPOST/PUT/DELETE)
Step 2 — Migrate all CDF access to the Cognite SDK
All traffic to Cognite Data Fusion (CDF) must go through the official Cognite SDK. Find any HTTP, WebSocket, or other network call to CDF-like hosts or APIs that bypasses the SDK and rewrite it to use the SDK.
Search for raw HTTP calls
# Find fetch, axios, XMLHttpRequest, and other HTTP client usage
grep -rn --include="*.ts" --include="*.tsx" --include="*.js" \
-E "(fetch\(|axios\.|axios\(|XMLHttpRequest|\.ajax\(|http\.get\(|http\.post\(|request\()" src/
# Find raw URL construction that looks like CDF endpoints
grep -rn --include="*.ts" --include="*.tsx" \
-E "(cognitedata\.com|cognite\.ai|/api/v1/projects|cdf\.|\.cognite\.)" src/
# Find custom Authorization or api-key headers
grep -rn --include="*.ts" --include="*.tsx" \
-E "(Authorization|api-key|apikey|x-api-key)" src/ | grep -v "node_modules"
How to fix
For each raw CDF call found, read the surrounding code to understand what CDF resource and operation it targets, then rewrite it using the appropriate SDK method. Remove the raw HTTP client import if it's no longer used.
| Pattern | Action |
|---|---|
fetch() or axios call to a CDF URL (*.cognitedata.com, /api/v1/projects/*) |
Rewrite to use the Cognite SDK (cognite.files.getDownloadUrls(...), cognite.timeseries.retrieve(...), client.instances.search(...), etc.) |
Custom Authorization header with a CDF token |
Remove — the SDK handles auth automatically |
| WebSocket connection to CDF endpoints | Rewrite to use SDK streaming methods |
| Proxy endpoint that forwards to CDF internally | Rewrite the proxy to use the SDK internally |
fetch() to a non-CDF URL (static assets, documented third-party API) |
Leave — but add a comment documenting why it's needed |
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.
- 2mo ago Changed · +1 lines 735a0242d149
- 2mo ago First seen · 249 lines · 119 tokens per session scan A c7c4cc9ce010
security is a skill published in the GitHub repository cognitedata/builder-skills (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 119 tokens to every session and 2,860 once invoked, about $0.0005 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 2026-08-31.
security compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| securitycognitedata/builder-skills | Skill | 6 | yesterday | Apache-2.0 | A | 119 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |