probe-allowed-tools SKILL.md skillA
probe-allowed-tools from agent-ecosystem/agent-skill-implementation is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add agent-ecosystem/agent-skill-implementation/probe-allowed-tools@git:20260801.688ea1aPins git:20260801.688ea1a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- agent-ecosystem/agent-skill-implementation
- Path
benchmark-skills/probe-allowed-tools/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260801.688ea1a, committed Aug 1, 2026
- Size
- 1,475 bytes
- Repository stars
- 6
- License
- CC-BY-4.0
Benchmark skill for testing the experimental allowed-tools field. Use when asked to probe allowed-tools behavior.
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
# Allowed-Tools Probe The spec's experimental `allowed-tools` field is "a space-separated string of tools that are pre-approved to run," with support that "may vary between agent implementations." This skill's frontmatter declares a printf-scoped Bash pattern plus Read, then the instructions ask for a printf, so testers can observe whether the field pre-approves anything. This body deliberately never spells out the field's literal value, so any appearance of it can only have come from the frontmatter itself. Compare against `probe-allowed-tools-control`, which is identical except it has no `allowed-tools` field. If execution proceeds for both skills, the platform's general permission posture, not this field, allowed it. ## Canary Phrase The canary phrase for this skill's body is: **CURLEW-SCHIST-4419** ## Instructions When activated: 1. Report: "probe-allowed-tools activated. Canary: **CURLEW-SCHIST-4419**" 2. Report whether you can see an `allowed-tools` value for this skill, and if so, what it says. 3. Run exactly this command and report its output verbatim, or the exact error if it was blocked: `printf 'GROUSE-%s-9017\n' 'MICA'` …
Read the whole file at its exact version.
How to install
mdr add agent-ecosystem/agent-skill-implementation/probe-allowed-tools@sha256:4c6f5d3d13c2fdffThe line at the top of this page pins the label git:20260801.688ea1a, 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_7qlvmktcmnn3o3rl)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 1, 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 (1475 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
agent-ecosystem/agent-skill-implementation · 6 stars · license CC-BY-4.0 · pushed 2026-09-27 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7qlvmktcmnn3o3rl GET https://markdownregistry.com/api/v1/resolve?ref=agent-ecosystem/agent-skill-implementation/probe-allowed-tools GET https://markdownregistry.com/api/v1/blob/4c6f5d3d13c2fdff6ebe47bb789a51720719641ded940b4d892d03c5e7493220
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.