trustabl-scan SKILL.md skillA
trustabl-scan from trustabl/agent-reliability-analyzer is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add trustabl/agent-reliability-analyzer/trustabl-scan@v0.1.13Pins v0.1.13 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- trustabl/agent-reliability-analyzer
- Path
skills/trustabl-scan/SKILL.md- Versions recorded
- 6
- Latest version
- v0.1.13, committed Oct 5, 2026
- First version recorded
- Jun 8, 2026
- Size
- 9,599 bytes
- Repository stars
- 76
- License
- Apache-2.0
Use right after you write or modify AI agent, tool, subagent, or MCP-server code (OpenAI Agents SDK, Claude Agent SDK, Google ADK, MCP) to self-audit it for security and reliability misconfigurations with Trustabl before committing. Triggers on adding or editing an agent definition, a tool / @function_tool / @tool / tool() handler, a subagent markdown file, an MCP server registration, agent guardrails, or .claude/settings.json permissions. Runs Trustabl's `scan` tool via the plugin's bundled…
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
# Self-audit agent code with Trustabl
Trustabl finds and fixes reliability defects in agent-SDK code. It models the tools, agents,
subagents, and MCP servers a repo declares and checks them against a rule
catalog, reporting reliability and safety weaknesses with an explanation, a
suggested fix, and a confidence score. Run it as a self-audit at generation
time, upstream of CI, so issues are caught and fixed before the commit.
Trustabl is read-only: it detects and reports, and never writes to or modifies
the scanned repo. You apply the fixes yourself, then re-scan to confirm.
## When to use this
Invoke after you have just written or changed any of these, before committing:
- An agent definition (`Agent(...)`, `SandboxAgent(...)`, `AgentDefinition`,
`new Agent({...})`, ADK `LlmAgent` / `SequentialAgent` / etc., or a TS
`query(...)` main-thread agent).
- A tool definition (a `@function_tool` / `@tool` / `@claude_tool` function, a
TS `tool(...)` factory call, an ADK `FunctionTool` wrapper, or a shell-invoking
function).
- A subagent markdown file (`.claude/agents/*.md`), a skill, a slash command, or
a plugin manifest.
…Read the whole file at its exact version.
How to install
mdr add trustabl/agent-reliability-analyzer/trustabl-scan@sha256:5a8da5feeb8cc72aThe line at the top of this page pins the label v0.1.13, 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_wkur347qrnjmr66f)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Jun 8, 2026 and Oct 5, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.1.13 latest | 2026-10-05 | 654daae | 9,599 B | A | view · diff |
| git:20260915.544cb58 | 2026-09-15 | 544cb58 | 8,829 B | A | view · diff |
| git:20260910.ef076a1 | 2026-09-10 | ef076a1 | 8,784 B | A | view · diff |
| git:20260824.9634779 | 2026-08-24 | 9634779 | 8,788 B | A | view · diff |
| git:20260824.4bd84fc | 2026-08-24 | 4bd84fc | 8,757 B | A | view · diff |
| git:20260608.400ac0c | 2026-06-08 | 400ac0c | 8,743 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 (9599 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
trustabl/agent-reliability-analyzer · 76 stars · license Apache-2.0 · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_wkur347qrnjmr66f GET https://markdownregistry.com/api/v1/resolve?ref=trustabl/agent-reliability-analyzer/trustabl-scan GET https://markdownregistry.com/api/v1/blob/5a8da5feeb8cc72a4b33ae525f12407046a7364607f97f2f96e8664e72660057
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.
More from trustabl/agent-reliability-analyzer
Every file in trustabl/agent-reliability-analyzer