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 security-auditgit 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/security-audit)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/security-audit"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/security-audit/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/security-audit"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 Server-Side Request Forgery · line 107 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high YARA Match · line 145 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium MCP Rug Pull · line 221 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
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 | $0.00041 | $0.04203 |
| Opus 5 | $0.00020 | $0.02101 |
| Sonnet 5 | $0.00008 | $0.00841 |
| Haiku 4.5 | $0.00004 | $0.00420 |
Grade B, and why
security-audit scanned grade B with 2 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- **Testing:** Point the application at internal services (`http://169.254.169.254/`, `http://localhost:9200/`). 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.
- **Testing:** Run scanners (Nuclei, Nikto), manual header inspection with curl/burp. How it starts
The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit Skill
A systematic approach to evaluating the security posture of applications, systems, and infrastructure. This skill equips you with the methodology, tooling, and reporting standards needed to conduct professional-grade security audits.
Core Principles
1. Defense in Depth
Security is not a single control but layered protections. An audit must evaluate each layer independently and in combination. A failure in one layer should be caught by another.
2. Least Privilege
Every component, user, and process should have the minimum permissions necessary to function. Audits must verify that privilege boundaries are enforced, not just declared.
3. Assume Breach
Design and audit with the assumption that an attacker has already compromised some part of the system. What can they access? What can they pivot to?
4. Repeatability
Audit procedures must be reproducible. If two auditors run the same methodology against the same target, they should reach consistent conclusions.
5. Evidence-Based Findings
Every finding must be backed by reproducible evidence — a screenshot, a log entry, a network capture, or a code path. "Trust me" is not a finding.
6. Continuous Improvement
A security audit is a snapshot in time. The goal is not just to find bugs but to improve the process so fewer bugs are introduced in the future.
Security Audit Maturity Model
| Level | Name | Description |
|---|---|---|
| L0 | Ad Hoc | No formal audits. Security reviews happen reactively after incidents. |
| L1 | Basic | Manual vulnerability scanning with off-the-shelf tools. No standardized methodology or reporting. |
| L2 | Defined | Formal audit methodology documented. OWASP Top 10 covered. Findings tracked with CVSS scoring. |
| L3 | Integrated | Audits integrated into CI/CD pipeline. SAST/SCA runs on every commit. DAST runs on staging. Dedicated threat modeling sessions. |
| L4 | Proactive | Continuous security validation. Red team exercises. Bug bounty program. Attack surface management automated. Security metrics tracked over time. |
| L5 | Adaptive | Automated remediation for common findings. AI-assisted threat modeling. Self-healing security controls. Audit findings feed back into developer training. |
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 · 422 lines · 41 tokens per session scan B 011777906709
security-audit is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (471 stars, last pushed 17d ago), licensed MIT. It adds 41 tokens to every session and 4,203 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (cloud metadata endpoint, makes network calls). 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.