agent-instructions-red-team SKILL.md skillA
agent-instructions-red-team from kesslernity/awesome-copilot-agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kesslernity/awesome-copilot-agent-skills/agent-instructions-red-team@git:20260917.f14a4fbPins git:20260917.f14a4fb in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kesslernity/awesome-copilot-agent-skills
- Path
skills/meta-skills/agent-instructions-red-team/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260917.f14a4fb, committed Sep 17, 2026
- First version recorded
- Sep 16, 2026
- Size
- 10,229 bytes
- Repository stars
- 15
- License
- CC-BY-SA-4.0
Reviews the instructions text and skills of a declarative agent, with its stated capabilities, knowledge sources and audience, for prompt-injection exposure, data-leakage paths, over-broad permissions and missing refusals, and returns an attack-surface map, a findings table with severity, quoted evidence and attack path, one pasteable fix per finding, a probe pack the owner can run and a refusal-coverage table. Use when the user asks to "red-team this agent…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Agent instructions red team ## Purpose Read an agent's instructions text, its skills and its stated capabilities, knowledge sources and audience, and produce one DRAFT review of how the agent could be turned against its owner: retrieved content that steers it, paths by which data reaches someone not entitled to it, capabilities and sources wider than the purpose needs, and requests it should decline but does not. Every finding carries a severity, quoted evidence, the attack path and one pasteable fix. ## When to use Use when the user asks to red-team, harden, stress-test or security-review an agent's instructions, system prompt or skill set, asks whether the agent could leak data or be hijacked by a document, or asks what it should refuse. Do not use for checking one SKILL.md against the format rules, use skill-file-reviewer instead. Do not use for designing the launch test set, use agent-evaluation-plan instead; this skill hands it the probe pack. ## Inputs 1. Instructions text, pasted, attached or reachable through this agent's configured knowledge sources. Partial text is reviewed as far as it goes; the rest is UNKNOWN. If unreachable, ask for a paste and say so. …
Read the whole file at its exact version.
How to install
mdr add kesslernity/awesome-copilot-agent-skills/agent-instructions-red-team@sha256:2ee525c332dc8e85The line at the top of this page pins the label git:20260917.f14a4fb, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_tszb2xd5fvplz2la)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 16, 2026 and Sep 17, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260917.f14a4fb latest | 2026-09-17 | f14a4fb | 10,229 B | A | view · diff |
| git:20260916.44af39e | 2026-09-16 | 44af39e | 10,225 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10229 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kesslernity/awesome-copilot-agent-skills · 15 stars · license CC-BY-SA-4.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_tszb2xd5fvplz2la GET https://markdownregistry.com/api/v1/resolve?ref=kesslernity/awesome-copilot-agent-skills/agent-instructions-red-team GET https://markdownregistry.com/api/v1/blob/2ee525c332dc8e854f3fba0085e514bdcbca3114de3de7e08a5a9e5a5398170d
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.