unboundcompute/security-agent-skills · skills/auditing-skill-and-mcp-instructions/SKILL.md

auditing-skill-and-mcp-instructions skillB

auditing-skill-and-mcp-instructions is agent-read markdown (skill) from unboundcompute/security-agent-skills: Lint the natural-language instruction text of an agent skill or MCP server, not its code: the skill body, the frontmatter description, tool descriptions, and parameter text a model reads and obeys. Covers instructions hidden in comments or markup, invisible and look-alike Unicode, override phrases that countermand earlier instructions, concealment directives that tell the agent to hide an action from the user, and instructions that steer the agent to read secrets and send them out. Use when revi.

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-skill-and-mcp-instructions@git:20260818.ed96156
Exact content
mdr add unboundcompute/security-agent-skills/auditing-skill-and-mcp-instructions@sha256:c7edb200d04489cf

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_eyf7hfkj23n5wwnw.svg)](https://markdownregistry.com/a/art_eyf7hfkj23n5wwnw)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260818.ed96156 latest2026-08-18 ed96156 7,264 BB view

Audit of the latest version

B  16 of 17 checks passed. Deterministic, no model, same answer every run.
  • fail: No prompt-injection phrasing (matched: ignore the previous instructions)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7264 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 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_eyf7hfkj23n5wwnw
GET https://markdownregistry.com/api/v1/resolve?ref=unboundcompute/security-agent-skills/auditing-skill-and-mcp-instructions
GET https://markdownregistry.com/api/v1/blob/c7edb200d04489cf3a2373f2a1e212f111999018af5efcf93f41e5af6aaa2274

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