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 Stijnman/grok-custom-skills --skill defensive-mcp-auditgit clone --depth 1 https://github.com/Stijnman/grok-custom-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/stijnman/grok-custom-skills/defensive-mcp-audit)<a href="https://agentmods.dev/skills/stijnman/grok-custom-skills/defensive-mcp-audit"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/defensive-mcp-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/stijnman/grok-custom-skills/defensive-mcp-audit"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/defensive-mcp-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.00589 |
| Opus 5 | $0.00026 | $0.00295 |
| Sonnet 5 | $0.00010 | $0.00118 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
defensive-mcp-audit 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 12d 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.
What it actually says
Defensive MCP Audit
When to Use
- User says audit mcp or task matches this capability
- User says mcp security or task matches this capability
- User says localhost exposure or task matches this capability
- User says defensive-mcp-audit or task matches this capability
Workflow
- Confirm audit is read-only; no port scanning beyond localhost inventory.
- Run: python3 -m defensive_mcp_audit (or pip install defensive-mcp-audit[cli]).
- Parse risk_level, risk_score, and findings table.
- Explain each finding in plain language with remediation (bind localhost, disable service).
- Never suggest attack techniques, malware, or penetration tests.
- Offer HTML/JSON export path; do not upload reports externally without user consent.
Integrations
exposed-service-triagemcp-tool-scouthitl-approver
Error Handling
| Failure | Response |
|---|---|
| Tool not installed | pip install defensive-mcp-audit[cli] or clone github.com/Stijnman/defensive-mcp-audit. |
| Permission denied on ss | Report limitation; suggest user-run with adequate permissions. |
Gotchas
- Defensive only — inspection, not exploitation.
Safety & Ethics (Publication-Ready)
This skill is designed for public distribution. Constraints:
- Read-only inspection; no network attacks or exploitation.
- Reports stay local unless user explicitly requests upload.
- Remediation advice is configuration-only (bind, disable, firewall).
Prohibited actions
- No unauthorized access, malware, or harmful automation
- No silent exfiltration of data, credentials, or telemetry
- No destructive system changes without hitl-approver
- No publication of user PII or environment secrets in outputs
Attribution
- Wraps the MIT-licensed defensive-mcp-audit project by Stijnman.
Example
Input: User request matching triggers above. Output: Structured result per workflow; local artifacts only unless user opts in.
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.
- 12d ago First seen · 71 lines · 52 tokens per session scan A 06257ab6f55d
defensive-mcp-audit is a skill published in the GitHub repository Stijnman/grok-custom-skills (9 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 589 once invoked, about $0.0003 per session on Opus 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.
Other skills, from other repositories
goal-meta-skill
A guide for turning an unclear or complex task into a reviewable /goal instruction for coding agents.
workflow-to-skill
Turn a goal and existing CLI, MCP, HTTP, API, or external workflow capabilities into one reviewable reusable Agent Skill. Use when the user asks to create or revise a workflow SKILL.md without a dedicated interface for invocation or result presentation. A webpage, UI, image, or report produced as workflow output does…
rss-digest
Collect RSS or Atom sources and produce a traceable intelligence digest through the configured Weft workflow.
workflow-docs-sync
A project-documentation synchronisation workflow for rebuilding project facts from a local Git folder, GitHub repository, or current working directory, then updating core workflow documents.
workflow-to-skill-with-surface
Create or revise one reusable workflow Skill plus an optional harness-native Prompt Surface that maps a dedicated form, Page, button set, command UI, or result view to ordinary Skill messages and Harness results. Use only when the user explicitly requests a dedicated interface for invoking the Skill or presenting its…
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.