defensive-mcp-audit is agent-read markdown (skill) from stijnman/grok-custom-skills: Run a defensive, read-only audit of local MCP and AI-agent exposure, including risky bindings, configuration issues, and confused-deputy risks. Use for: audit MCP, MCP security, localhost exposure, defensive MCP audit..
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.
mdr add stijnman/grok-custom-skills/defensive-mcp-audit@v1.1.0mdr add stijnman/grok-custom-skills/defensive-mcp-audit@sha256:06257ab6f55db1c7Pin 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.
[](https://markdownregistry.com/a/art_t5iblj2sxd3doqi4)
0 badge views in 30 days
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.0 latest | 2026-08-14 | 80f2e55 | 2,547 B | A | view · diff |
| v1.1.0 | 2026-08-14 | abe185a | 2,560 B | A | view · diff |
| v1.0.0 | 2026-06-24 | 5c9866b | 2,740 B | A | view |
stijnman/grok-custom-skills · 9 stars · license MIT · pushed 2026-09-06 · branch main
GET https://markdownregistry.com/api/v1/artifacts/art_t5iblj2sxd3doqi4 GET https://markdownregistry.com/api/v1/resolve?ref=stijnman/grok-custom-skills/defensive-mcp-audit GET https://markdownregistry.com/api/v1/blob/06257ab6f55db1c713dc7dcf0582edb62cf82bdfcf63ae278f671b6e8dc368ac