AC multi-agent-sandbox
Setup multi-agent sandbox infrastructure with Docker, Discord, SSH, and Tailscale. Use when: (1) creating a sandboxed agent for cross-gateway collaboration, (2) setting up Discord multi-bot with separate accounts and requireMention gating, (3) configuring socat bridges for container→VPS SSH via Tailscale, (4) enabling bidirectional agent-to-agent communication via sessions_send with per-agent A2A allowlists, (5) sharing a VPS workspace between agents from different OpenClaw gateways, (6) isolating sandbox agents from main agent private data.
As a process C 64/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
low Dangerous commands
cmd-background-processSKILL.md:196Starts a background / autostarted process (documentation of a security skill)sudo systemctl enable --now soca…way soca…ssh
security skill -
low Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:271Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)curl -fsSL https://tailscale.com/install.sh | sh
security skill
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 60Failures and branches. 2 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 19 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2358 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 547: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.