BD clawlock
ClawLock — 综合安全扫描、红队测试与加固工具，支持全平台。 当用户明确要求安全扫描、安全体检、安全加固时触发： 「开始安全体检」「安全扫描」「检查 skill 安全」「安全加固」「探测实例」 「scan my claw」「security check」「drift detection」「red team」「红队测试」 「React2Shell」「agent-scan」「发现安装」「凭证权限」 Do NOT trigger for general coding, debugging, or normal Claw usage.
As a process D 49/100 · 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 · 8
✓ No critical or high findings
Medium and low: 8
-
low Risky intent
intent-offensive-securitySKILL_EN.md:8Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)"drift detection" "red team test" "React2Shell"
detector -
low Dangerous commands
cmd-privilegeSKILL_EN.md:224Privilege escalation / world-writable permissions (documentation of a security skill)🔴 Crit (confirmed malicious): credential exfil (curl/wget) · reverse shell (bash/nc/Python/mkfifo) · crypto mining · destructive deletion · chmod 777 · prompt injection (override/hijack/jailbreak/Chi
security skill -
low Risky intent
intent-offensive-securitySKILL_EN.md:224Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)🔴 Crit (confirmed malicious): credential exfil (curl/wget) · reverse shell (bash/nc/Python/mkfifo) · crypto mining · destructive deletion · chmod 777 · prompt injection (override/hijack/jailbreak/Chi
detector -
low Risky intent
intent-offensive-securitySKILL_EN.md:433Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **No privilege escalation:** Never use `sudo` / `chmod -R 777` / cross-user writes / system-service installs / disabling SELinux or AppArmor
-
low Risky intent
intent-offensive-securitySKILL.md:7Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)「scan my claw」「security check」「drift detection」「red team」「红队测试」
detector
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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 49/100
- 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
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4389 tokens
- 100Steps. 89 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 18 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
- -2localhost URLs: will not work for another user
- -266 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 270: enough signal without eating the budget
- +4Structure: 39 headings
- +3Step-by-step instructions: 89 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.