AB examine-sandbox
Use this skill when the user wants to check what data their shared agent can access, inspect what's being shared, review privacy, or see what guests will see. Triggers on: 'what can they see', 'check my link', 'audit my agent', 'review what I'm sharing', or 'what data is shared'.
As a process B 65/100 · Nearly there — weak spots: result and completion, failures and branches, progress reporting
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 Exfiltration
net-credential-useSKILL.md:23Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s -H "Authorization: Bearer $PULSE_API_KEY" \
security skill -
low Exfiltration
net-credential-useSKILL.md:36Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s -H "Authorization: Bearer $PULSE_API_KEY" \
security skill
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 65/100
- 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
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 10 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 546 tokens
- 100Running it twice. No mutating operations
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
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 280: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.