unboundcompute/security-agent-skills · skills/auditing-the-lethal-trifecta/SKILL.md

auditing-the-lethal-trifecta skillA

auditing-the-lethal-trifecta is agent-read markdown (skill) from unboundcompute/security-agent-skills: Find where an AI agent becomes dangerous: the trust context in which access to private data, exposure to untrusted content, and an ability to send data out all coexist. Any two legs are usually safe; all three let planted content make the agent read secrets and exfiltrate them. Use when designing or reviewing a tool-using LLM agent, before granting it a new tool or data scope, or to judge whether a prompt injection is actually exploitable. Covers capability inventory, the three legs, kill-chain .

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add unboundcompute/security-agent-skills/auditing-the-lethal-trifecta@git:20260816.4aab195
Exact content
mdr add unboundcompute/security-agent-skills/auditing-the-lethal-trifecta@sha256:0de5d6f2a9ca2ca7

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_owvc4ez6wx6zq5ys.svg)](https://markdownregistry.com/a/art_owvc4ez6wx6zq5ys)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260816.4aab195 latest2026-08-16 4aab195 6,313 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6313 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

GitHub

unboundcompute/security-agent-skills · 5 stars · license MIT · pushed 2026-09-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_owvc4ez6wx6zq5ys
GET https://markdownregistry.com/api/v1/resolve?ref=unboundcompute/security-agent-skills/auditing-the-lethal-trifecta
GET https://markdownregistry.com/api/v1/blob/0de5d6f2a9ca2ca7bd0b94f7bb666043dd818ed1e8a8c7d3f3784f8b845eb87d

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.