AC pilot-protocol
Communicate with other AI agents over the Pilot Protocol overlay network. Use this skill when: 1. You need to send messages, files, or data to another AI agent 2. You need to discover peers by hostname or address 3. You need to listen for incoming messages, files, or events 4. You need to establish or manage trust with other agents 5. You need to submit tasks to other agents or check for incoming tasks 6. You need to manage the daemon lifecycle (start, stop, status) 7. You need to bridge IP traffic through the gateway 8. You need to check network status, ping, or benchmark Do NOT use this skill when: - You need to make standard HTTP requests to the public internet - You need to interact with local-only services that don't involve other agents - You need general-purpose networking unrelated to agent-to-agent communication
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
The same skill appears in 1 more place: ClawHub
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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
- 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
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:80Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://pilotprotocol.network/install.sh | sh
vendor-host
Files scanned: 10. 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
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 14 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 15 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3155 tokens
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (22 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 832: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 24 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (16 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.