AC ai-safety-guard
Lightweight passive privacy guard for OpenClaw — intelligently prevents user data from leaking externally. TRIGGER: before the AI sends or outputs any data to an external destination (API call, email, MCP, upload, post, share, webhook, clipboard copy that goes external etc.). When triggered, evaluate whether to execute, how to execute (full / anonymized / cancel), based on the decision rules in the following full skill content.
As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 5
✓ No critical or high findings
Medium and low: 5
✓ Guard found no suspicious behaviour. 5 matches are attack strings quoted in this security skill's own documentation.
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 57/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Failures and branches. 2 branches
- 100Tools and files. No external tools needed
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2130 tokens
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 431: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.