unboundcompute/security-agent-skills · skills/auditing-ai-agent-permissions/SKILL.md

auditing-ai-agent-permissions skillA

auditing-ai-agent-permissions is agent-read markdown (skill) from unboundcompute/security-agent-skills: Audit what an AI agent is actually allowed to do versus what its task needs. Covers excessive agency (tools, scopes, and autonomy beyond the job), missing human-in-the-loop gates on irreversible actions, over-broad credentials and their blast radius, sandbox and code-interpreter escape, unfiltered egress, and unbounded resource or spend (denial-of-wallet). Use when granting an agent a tool or scope, reviewing an agent's permission posture, or deciding which actions need approval. The model's res.

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-ai-agent-permissions@git:20260816.a6124f2
Exact content
mdr add unboundcompute/security-agent-skills/auditing-ai-agent-permissions@sha256:28e145fe926a3f78

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_bwzj6a4cjy6fypwf.svg)](https://markdownregistry.com/a/art_bwzj6a4cjy6fypwf)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260816.a6124f2 latest2026-08-16 a6124f2 6,583 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 (6583 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_bwzj6a4cjy6fypwf
GET https://markdownregistry.com/api/v1/resolve?ref=unboundcompute/security-agent-skills/auditing-ai-agent-permissions
GET https://markdownregistry.com/api/v1/blob/28e145fe926a3f78de3d475a438206952811d2f31d0c2528a821ab38ce7b5bc6

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