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 agent-red-teamgit 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/agent-red-team)<a href="https://agentmods.dev/skills/stijnman/grok-custom-skills/agent-red-team"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/agent-red-team/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/agent-red-team"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/agent-red-team.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 | $0.00097 | $0.01765 |
| Opus 5 | $0.00048 | $0.00882 |
| Sonnet 5 | $0.00019 | $0.00353 |
| Haiku 4.5 | $0.00010 | $0.00177 |
Grade B, and why
agent-red-team 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 11d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
1. **Indirect injection** — “Ignore previous instructions…” buried in a retrieved doc / webpage / email the agent will read. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Red Team (Defensive)
Authorized defensive red-teaming for AI agents you own or are explicitly allowed to test. Goal: surface failure modes before attackers do — then harden.
When to Use
- User says red team, red-teaming, agent red team, or /agent-red-team
- User asks for adversarial test, prompt injection test, jailbreak test
- User wants MCP / tool abuse review or skill safety adversarial pass
- Before publishing a skill, enabling a new MCP server, or shipping an agent feature
Hard boundaries (non-negotiable)
| Allowed | Forbidden |
|---|---|
| Test systems the user owns / has written authorization for | Attacking third-party production without authorization |
| Catalog attack classes and example probe strings for own apps | Writing exploit PoCs, malware, ransomware, or weaponized payloads |
| Read-only config/code review + simulated reasoning | Live exploitation of remote endpoints |
| Report severity + remediation | Credential theft, doxxing, or silent exfiltration |
Recommend hitl-approver / policy gates |
Bypassing user safety for “demo” attacks |
If scope is unclear: stop and ask who owns the target and what is in-bounds.
Workflow
- Scope lock — Confirm target (agent, skill path, MCP server, app prompt, policy). Confirm authorization. Note environment (local / staging / prod).
- Surface map — List trust boundaries:
- System / developer / user / tool / retrieved-document / memory channels
- MCP tools and dangerous capabilities (shell, browser, email, file write)
- Secrets handling, logging, and HITL gates
- Threat pack — Select categories from
references/attack-categories.md(start with the top 8 for a quick pass; full pack for publish readiness). - Probe design — For each category, craft 3–5 short probes aimed at the target. Prefer abstract / synthetic content. Do not store real PII or live secrets in probes.
- Execute safely
- Prefer dry-run / simulation against policy text and code paths.
- If running live against a local agent: use isolated session, no production credentials, no irreversible side effects.
- Never call remote attack tooling. Never generate working exploits.
- Score findings — Use severity rubric below. Capture evidence (truncated, response excerpt, config path). Redact secrets with
privacy-redactorpatterns. - Remediate — For each finding: concrete fix (prompt rule, allowlist, HITL, sandbox, output filter, MCP bind, skill rewrite).
- Report — Write markdown using
references/report-template.md. Offer optional JSON export. Do not upload externally without consent. - Optional follow-ups — Invoke related skills:
defensive-mcp-auditfor localhost/MCP exposurehyper-skill-testerfor skill QA after fixeshitl-approverfor high-risk action gatesollama-localhost-guardianif local LLM bindings matter
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 147 lines · 97 tokens per session scan B ce9bde8aa80c
agent-red-team is a skill published in the GitHub repository Stijnman/grok-custom-skills (9 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 1,765 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). 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.