BD SX-security-audit
全方位安全审计技能。检查文件权限、环境变量、依赖漏洞、配置文件、网络端口、Git 安全、Shell 安全、macOS 安全、密钥检测等。支持 CLI 参数、JSON 输出、配置文件。当用户要求"安全检查"、"漏洞扫描"、"权限检查"、"安全审计"时使用此技能。
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 2 more places: ClawHub, ClawHub
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Secrets in code
secret-private-keySKILL.md:72Private key material (key header without key body; documentation table row)| Private Key | `-----BEGIN PRIVATE KEY----- …
header onlytable -
low Secrets in code
secret-password-literalreferences/code-security.md:92Hard-coded password / key literal (may be an example) (placeholder value)const apiKey = "sk-p…...";
placeholder -
low Secrets in code
secret-aws-keyreferences/secrets-detection.md:11AWS access key ID (placeholder value)| AWS Access Key | `AKIA[0-9A-Z]{16}` | `AKIA…PLE` |placeholder -
low Secrets in code
secret-github-tokenreferences/secrets-detection.md:12GitHub token (placeholder value)| GitHub Token (classic) | `ghp_[a-zA-Z0-9]{36}` | `ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx` |placeholder
Files scanned: 8. 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")
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) that frontmatter does not declare
- 100Steps. 47 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 858 tokens
- 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
- -215 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 130: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 47 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.