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 cosmicstack-labs/mercury-agent-skills --skill secure-codinggit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-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/cosmicstack-labs/mercury-agent-skills/secure-coding)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/secure-coding"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/secure-coding/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/cosmicstack-labs/mercury-agent-skills/secure-coding"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/secure-coding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 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 524 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 Privilege Escalation · line 638 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 642 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high YARA Match · line 748 YARA rule matched a known webshell pattern (PHP, Python, JSP, or ASPX webshell).Fix: Remove the webshell code immediately. Webshells provide unauthorized remote command execution. Audit the skill for additional backdoors or persistence mechanisms.
- high Privilege Escalation · line 763 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 326 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 314 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 328 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00043 | $0.06177 |
| Opus 5 | $0.00022 | $0.03089 |
| Sonnet 5 | $0.00009 | $0.01235 |
| Haiku 4.5 | $0.00004 | $0.00618 |
Grade A, and why
secure-coding scanned grade A 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 8d 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.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
response = requests.post( "https://provider.com/oauth2/token", 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.
response = requests.post( Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`eval(request.body.expression)` is a remote code execution vulnerability. Same for `exec()`, `os.system()`, and template engines with user-controlled templates. How it starts
The opening of the file, as written. The whole thing — 788 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secure Coding Skill
Writing code that is resistant to attack requires intentional practices at every layer. This skill covers the fundamental security patterns every developer should implement: input validation, authentication, authorization, cryptography, secrets management, and error handling.
Core Principles
1. Never Trust User Input
All input is guilty until proven innocent. Validate, sanitize, and parameterize every piece of data that crosses a trust boundary — HTTP requests, file uploads, database queries, API calls, message queue payloads.
2. Fail Securely
When something goes wrong, the default behavior should be denial, not access. An error should reject the request, log the event, and return minimal information to the user.
3. Defense in Depth
No single control is sufficient. If input validation fails, parameterized queries should prevent injection. If authentication is bypassed, authorization should block access. Layer your defenses.
4. Keep Security Simple
Complex cryptography, custom authentication schemes, and convoluted permission models are more likely to have bugs. Use well-vetted libraries. Do not roll your own crypto.
5. Least Privilege
Every component, function, and user should have the minimum permissions required to do its job. Apply this to database accounts, API keys, file permissions, and cloud IAM roles.
6. Secure by Default
Features should be secure out of the box. Developers should have to explicitly weaken security, not opt into it. Default deny, not default allow.
7. Don't Expose Internals
Error messages, stack traces, debug endpoints, and internal IPs should never reach the client. What the user doesn't know, they can't exploit.
Secure Coding Checklist
Use this checklist during code review and development:
Pre-Commit
- All user input validated (type, length, format, range)
- SQL queries use parameterized statements (no string concatenation)
- No secrets in source code (API keys, passwords, tokens)
- Authentication tokens are not logged
- Output is encoded for the target context (HTML, JS, CSS, URL)
- File uploads validated: extension, MIME type, file size
- No debug endpoints or admin panels accessible without auth
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.
- 8d ago First seen · 788 lines · 43 tokens per session scan A d935f5fd1cad
secure-coding is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (471 stars, last pushed 17d ago), licensed MIT. It adds 43 tokens to every session and 6,177 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 3 findings (sends data to an external url, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
modern-saas-builder
Founder-minded senior product engineer and SaaS architect skill. Use when building, planning, architecting, validating, designing, testing, securing, deploying, or monetizing modern SaaS products, micro-SaaS, web apps, AI agents, Web3/Base applications, agent commerce, or Telegram bots/Mini Apps. Always active when…
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.