polygraph SKILL.md skillA
polygraph from bankrbot/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add bankrbot/skills/polygraph@git:20260630.7bfb013Pins git:20260630.7bfb013 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- bankrbot/skills
- Path
polygraph/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260630.7bfb013, committed Jun 30, 2026
- First version recorded
- Jun 26, 2026
- Size
- 13,601 bytes
- Repository stars
- 1,209
- License
- none declared
Behavioral trust grades (A–F) for MCP servers. Use when an agent needs to check whether an MCP server is safe before using it, verify an onchain attestation before trusting or paying a server, look up a server's published grade, get a project graded, or understand why a server received a grade. Polygraph connects to an MCP server the way an agent would, fingerprints its exact tool surface, and runs behavioral probes — prompt-injection (C-01), permission/egress overreach (C-02), sensitive-data…
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
# Polygraph: Behavioral Trust Grades for MCP Servers Agents wire up third-party MCP servers and then trust whatever those servers' tools return. Polygraph tests an MCP server's **behavior** before your agent does, and assigns a letter grade **A–F** backed by reproducible evidence. A passing grade is a **measurement, not a guarantee** — it says "this exact tool surface did not misbehave under these probes," and because the harness is open and deterministic, anyone can re-run it and disprove a bad grade. That falsifiability is the whole point. - **Home / methodology:** [polygraph.so](https://polygraph.so) - **Lookup CLI (npm):** `polygraphso` - **Grading harness:** `@polygraphso/litmus` (open source) --- ## What a grade measures Polygraph connects to a server the way an agent would — **stdio** for local packages, **Streamable HTTP** for remote URLs — fingerprints its exact tool surface (`tools/list` → canonical JSON → sha256 → `bytes32`), then runs four probe categories: - **C-01 — Tool-output injection.** Does the server try to hijack the agent? Static scan of tool names/descriptions/schemas for injection-shaped content (invisible unicode, …
Read the whole file at its exact version.
How to install
mdr add bankrbot/skills/polygraph@sha256:c1fad077ea2ce5f4The line at the top of this page pins the label git:20260630.7bfb013, 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_fqqyrqgjqjybwvdw)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jun 26, 2026 and Jun 30, 2026, about one every day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260630.7bfb013 latest | 2026-06-30 | 7bfb013 | 13,601 B | A | view · diff |
| git:20260626.3eca93f | 2026-06-26 | 3eca93f | 10,026 B | A | view · diff |
| git:20260626.b39aabf | 2026-06-26 | b39aabf | 10,012 B | A | view · diff |
| git:20260626.c84909a | 2026-06-26 | c84909a | 11,600 B | A | view · diff |
| git:20260626.d3b35d9 | 2026-06-26 | d3b35d9 | 10,724 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 (13601 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
bankrbot/skills · 1,209 stars · license none declared · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fqqyrqgjqjybwvdw GET https://markdownregistry.com/api/v1/resolve?ref=bankrbot/skills/polygraph GET https://markdownregistry.com/api/v1/blob/c1fad077ea2ce5f4848756d1c26f22823aa384dae4eeafa77ff2b686bba8eebe
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.