FC arpc
Send and receive messages to other AI agents over the Agent Relay Protocol (ARP). Messages are end-to-end encrypted using HPKE (RFC 9180) and routed through a relay server using Ed25519 public keys as identities. Use when user wants to send messages to other agents, set up agent-to-agent communication, install or configure ARP, manage ARP contacts, or enable the OpenClaw bridge. Trigger phrases include "send a message to", "add ARP contact", "message agent", "set up ARP", "install arpc", "what is my ARP key", or "enable ARP bridge".
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 11
-
high Dangerous commands
cmd-pipe-to-shellreferences/installation.md:41Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://arp.offgrid.ing/install.sh | bash
-
high Dangerous commands
cmd-persistencereferences/uninstall.md:20Persistence mechanism (cron / launchd / scheduled task / autorun registry)rm -f ~/Library/LaunchAgents/ing.offgrid.arpc.plist
-
high Dangerous commands
cmd-pipe-to-shellreferences/uninstall.md:52Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://arp.offgrid.ing/install.sh | bash
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:32Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://arp.offgrid.ing/install.sh | bash
Medium and low: 7
-
medium Dangerous commands
cmd-pipe-to-shellreferences/installation.md:137Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- **Service not found** — re-run the installer: `curl -fsSL https://arp.offgrid.ing/install.sh | bash`
quoted -
medium Dangerous commands
cmd-pipe-to-shellreferences/troubleshooting.md:12Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row)| `command not found: arpc` | Run the installer: `curl -fsSL https://arp.offgrid.ing/install.sh \| bash` |
table -
medium Dangerous commands
cmd-pipe-to-shellreferences/troubleshooting.md:26Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row)| systemd service not found | Re-run the installer: `curl -fsSL https://arp.offgrid.ing/install.sh \| bash` — it creates the service file |
table -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:141Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row)| `command not found: arpc` | Run installer: `curl -fsSL https://arp.offgrid.ing/install.sh \| bash` |
table -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:183Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)**Quick update:** `arpc update` or `curl -fsSL https://arp.offgrid.ing/install.sh | bash`
quoted -
low Exfiltration
net-credential-usereferences/installation.md:401Credential used in a network call (verify the destination is the intended service) (detector / deny-list definition)- Test manually: `curl -H "Authorization: Bearer ${TOKEN}" http://127.0.0.1:${PORT}/api/v1/status`detector -
low Exfiltration
net-credential-usereferences/troubleshooting.md:71Credential used in a network call (verify the destination is the intended service) (detector / deny-list definition)- Test manually: `curl -H "Authorization: Bearer ${TOKEN}" http://127.0.0.1:${PORT}/api/v1/status`detector
Files scanned: 4. 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 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 19 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 30 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1781 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 538: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.