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
distributions/wshobson-agents/skills/trustabl-scan/SKILL.md- Versions recorded
- 1
- Latest version
- v0.1.13, committed Oct 9, 2026
- Size
- 4,663 bytes
- Repository stars
- 76
- License
- Apache-2.0
Use right after you write or modify AI agent, tool, subagent, or MCP-server code (Claude Agent SDK, OpenAI Agents SDK, Google ADK, Vercel AI SDK, Pydantic AI, LangChain, CrewAI, AutoGen, MCP) to audit it for reliability and safety defects before committing. Triggers on adding or editing an agent definition, a tool or @function_tool or @tool handler, a subagent markdown file, an MCP server registration, agent guardrails, or .claude/settings.json permissions. Runs the local `trustabl` CLI and…
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
# Audit agent code with Trustabl Trustabl models the agents, tools, subagents, skills and MCP servers a repository declares, then checks each against a versioned rule pack. Every finding names a file and line, explains why it matters, and carries a suggested fix and a confidence score. The analysis is static and deterministic. Trustabl never executes the agent, never writes to the scanned repository, and has no model in the analysis path. You apply the fixes; re-scanning confirms them. ## Before you run anything This skill drives the `trustabl` binary on the user's machine. It does not bundle one. Check first: ```bash trustabl --help ``` If that fails, the CLI is not installed. **Do not install it silently.** Tell the user it is missing, offer one of these, and wait for them to choose: ```bash brew install trustabl/tap/trustabl # macOS, Linux scoop bucket add trustabl https://github.com/trustabl/scoop-bucket # Windows scoop install trustabl ``` If the user would rather install nothing, Docker runs the same scan: ```bash docker run --rm -v "$PWD:/repo" ghcr.io/trustabl/trustabl:latest scan /repo ``` ## Running the scan …
Read the whole file at its exact version.
How to install
mdr add trustabl/agent-reliability-analyzer/trustabl-scan@sha256:9e9c2620e29a60f5The 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_xoocuz37yn7oi6yd)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 9, 2026.
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 (4663 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_xoocuz37yn7oi6yd GET https://markdownregistry.com/api/v1/resolve?ref=trustabl/agent-reliability-analyzer/trustabl-scan GET https://markdownregistry.com/api/v1/blob/9e9c2620e29a60f5b0f179d5498989c9f11d95723022986078c27e1df417376c
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