ai-agent-safety-and-red-team SKILL.md skillA
ai-agent-safety-and-red-team from peterbamuhigire/chwezi-dev-engine is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add peterbamuhigire/chwezi-dev-engine/ai-agent-safety-and-red-team@git:20260924.eb7972ePins git:20260924.eb7972e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- peterbamuhigire/chwezi-dev-engine
- Path
skills/ai/ai-agent-safety-and-red-team/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260924.eb7972e, committed Sep 24, 2026
- First version recorded
- May 19, 2026
- Size
- 16,708 bytes
- Repository stars
- 28
- License
- MIT
Use when red-teaming agent tool and data perimeters for indirect prompt injection, action escalation, tenant exfiltration, unsafe tool chains, self-modification, or containment regressions.
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
# AI Agent Safety and Red-Team Acknowledgement: Shared by Peter Bamuhigire, techguypeter.com, +256 784 464178. <!-- dual-compat-start --> ## Use When - Hardening an agent against **indirect prompt injection** — instructions embedded in the data the agent reads (KB chunk, web page, tool response, email body the agent summarises). - Defending against **action escalation** — agent chains a benign read tool with a high-privilege write tool to do something the user didn't authorise. - Defending against **tenant data exfiltration** — agent extracts tenant data and embeds it in a tool call argument that exits the boundary (webhook URL, email recipient, log message). - Defending against **recursive self-modification** — agent updates its own prompt, memory, or tool registry. - Standing up a **red-team CI suite** that fires nightly and on every prompt / tool / runtime change. ## Do Not Use When - The task is direct prompt injection in single-shot features — `ai-prompt-injection-and-tenant-safety`. - The task is generic AI security checklist — `ai-security`. - The task is platform-wide security review — `vibe-security-skill`. …
Read the whole file at its exact version.
How to install
mdr add peterbamuhigire/chwezi-dev-engine/ai-agent-safety-and-red-team@sha256:1b3faad9d6395afbThe line at the top of this page pins the label git:20260924.eb7972e, 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_pep2eytuhw2gctls)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between May 19, 2026 and Sep 24, 2026, about one every 32 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260924.eb7972e latest | 2026-09-24 | eb7972e | 16,708 B | A | view · diff |
| git:20260916.2b57163 | 2026-09-16 | 2b57163 | 16,628 B | A | view · diff |
| git:20260907.1b775c1 | 2026-09-07 | 1b775c1 | 15,828 B | A | view · diff |
| git:20260712.a867952 | 2026-07-12 | a867952 | 15,830 B | A | view · diff |
| git:20260519.bd4658a | 2026-05-19 | bd4658a | 15,082 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 (16708 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
peterbamuhigire/chwezi-dev-engine · 28 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pep2eytuhw2gctls GET https://markdownregistry.com/api/v1/resolve?ref=peterbamuhigire/chwezi-dev-engine/ai-agent-safety-and-red-team GET https://markdownregistry.com/api/v1/blob/1b3faad9d6395afbdd2cdf9ff46524e7634170de9b2959e18b0b82a260306e91
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.