exec-safety SKILL.md skillB
exec-safety from papadopouloskyriakos/agentic-chatops is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add papadopouloskyriakos/agentic-chatops/exec-safety@git:20260919.c129a05Pins git:20260919.c129a05 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- papadopouloskyriakos/agentic-chatops
- Path
openclaw/skills/exec-safety/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260919.c129a05, committed Sep 19, 2026
- Size
- 1,285 bytes
- Repository stars
- 106
- License
- none declared
Blocked command list for exec tool — commands that must NEVER be executed, even if asked.
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
# Exec Safety — BLOCKED COMMANDS (NEVER EXECUTE) The following commands are ABSOLUTELY FORBIDDEN via exec. Do NOT run them under any circumstances, even if asked: ``` rm -rf / # Wipe filesystem rm -rf /* # Wipe filesystem reboot # Reboot host (use maintenance companion) shutdown # Shutdown host init 0 / init 6 / halt # Shutdown/reboot poweroff # Power off mkfs # Format filesystem dd if=/dev/zero # Wipe disk > /dev/sda # Wipe disk kubectl delete namespace # Delete entire namespace kubectl delete --all # Delete all resources iptables -F # Flush firewall rules systemctl stop n8n # Stop n8n (breaks gateway) ``` Also NEVER pipe output to external hosts: - No `curl` or `wget` to non-*.example.net domains - No `nc`/`ncat` to external IPs - No `scp`/`rsync` to hosts outside the network If you need to perform a destructive or write operation, escalate to Claude Code instead.
Read the whole file at its exact version.
How to install
mdr add papadopouloskyriakos/agentic-chatops/exec-safety@sha256:1345d74a2f11039bThe line at the top of this page pins the label git:20260919.c129a05, 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_vgqc7hy4lpgzpip3)
6 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 19, 2026.
Audit of the latest version
- fail: No recursive delete of root, home or parent (matched: rm -rf / )
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (1285 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 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
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
papadopouloskyriakos/agentic-chatops · 106 stars · license none declared · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_vgqc7hy4lpgzpip3 GET https://markdownregistry.com/api/v1/resolve?ref=papadopouloskyriakos/agentic-chatops/exec-safety GET https://markdownregistry.com/api/v1/blob/1345d74a2f11039ba7712a8c22aaa5ef9f58955b28c853bde5ea5e68984241d3
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.