AD skill-sandbox
Sandboxed ClawHub skill installation with automated security scanning. Use when: (1) Installing any new skill from ClawHub, (2) Auditing an already-installed skill, (3) Promoting a quarantined skill after review. Installs skills to a staging area, runs a multi-layer static security scan (file inventory, code patterns, dangerous instructions, dependency analysis, publisher verification), then auto-promotes clean skills or quarantines flagged ones for manual review. Prevents supply chain attacks from untrusted skill publishers.
As a process D 43/100 · Unfinished process — 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Dangerous commands
cmd-privilegescripts/skill-sandbox.sh:289Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)"disable.*security\|ignore.*guardrail\|skip.*auth\|exfiltrate\|phone.home\|send.*to.*server\|upload.*data\|rm -rf /\|delete.*all\|chmod 777\|0\.0\.0\.0\|mkfifo\|nc -l\|reverse.shell\|>/etc/\|curl.*|.*
detectorcode literal
A further 1 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 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. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 29 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 771 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 531: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.