BD Sandbox & Blast-Radius Control Engine X∞
Lapisan keamanan eksekusi OpenClaw. Mengklasifikasi risiko, membatasi blast-radius, menerapkan least-privilege, isolation, dry-run, backup, rollback, dan verifikasi untuk setiap tindakan agent agar kesalahan agent tidak menyebar menjadi kerusakan sistem yang lebih luas.
Lapisan keamanan eksekusi OpenClaw.
As a process D 44/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
low Risky intent
intent-offensive-securitySKILL.md:640Offensive-security / dual-use content (legitimate for authorised testing; review intended use)17. PRIVILEGE ESCALATION
-
low Risky intent
intent-offensive-securitySKILL.md:710Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- privilege escalation
-
low Risky intent
intent-offensive-securitySKILL.md:1110Offensive-security / dual-use content (legitimate for authorised testing; review intended use)PRIVILEGE ESCALATION
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 7863 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "type" - note
frontmatter-keyunknown frontmatter key "risk_level" - note
frontmatter-keyunknown frontmatter key "xinf_compliance" - note
frontmatter-keyunknown frontmatter key "xinf_principles" - note
frontmatter-keyunknown frontmatter key "owner" - note
frontmatter-keyunknown frontmatter key "status"
Process rating: all ten parameters 44/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 28 mutating operations with no state check
- 40Consistency. Frontmatter name (Sandbox & Blast-Radius Control Engine X∞) differs from the folder (sandbox-blast-radius-control-engine)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 7863 tokens
- 100Steps. 193 steps
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4No input/output examples
- +2Single-language instructions
- +3Description length 270: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 193 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 51.