BC rules-of-the-claw
A strong, field-tested Guardian baseline for OpenClaw Guardian — 56 deterministic rules protecting against credential theft, data exfiltration, network scanning, and infrastructure destruction. No LLM voting overhead. Pure regex enforcement at the tool layer.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Exfiltration
read-dotenvrules-of-the-claw.json:701Reads a .env file (detector / deny-list definition)"description": "Block capturing sensitive file contents into shell variables (SECRET=$(cat .env), TOKEN=`cat ...`)",
detector -
low Exfiltration
read-dotenvrules-of-the-claw.json:893Reads a .env file (detector / deny-list definition)"description": "Block process substitution reading sensitive files (<(cat .env))",
detector
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, git, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1170 tokens
- low 10 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 259: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.