DF skill-security-checker
Skill Security — 安全审计扫描器，审一下这个 skill、装之前帮我查查、这个 skill 安全吗？一键快扫 30 秒出三档裁定（✅干净/⚠️可疑/🚫恶意）+ Top3 风险 + 一句话理由；全量模式覆盖轻量 SAST 污点追踪（Python AST + JS 词法近似，source→sink 证据链降误报）、规则引擎（YAML 规则包热插拔扩展）、社区规则（schema 校验 + 来源记录 + 签名验证）、提示注入 ML 语义检测（ONNX + 正则降级）、系统级行为捕获（eBPF Linux / ETW Windows）、动态沙箱执行扫描、供应链风险分析、OSV.dev 离线数据包（全生态 CVE 覆盖，零密钥）+ 锁文件深度解析（requirements.txt / package-lock.json / poetry.lock，版本区间级精确匹配）、恶意 Skill 指纹库、健康度与合规检查（质量+结构+权限合并）、全局排除配置、CI/CD 集成、JSON/HTML/SARIF 报告生成。
Skill Security — 安全审计扫描器，审一下这个 skill、装之前帮我查查、这个 skill 安全吗？一键快扫 30 秒出三档裁定（✅干净/⚠️可疑/🚫恶意）+ Top3 风险 + 一句话理由；全量模式覆盖轻量 SAST 污点追踪（Python AST + JS 词法近似，source→sink…
As a process F 33/100 · No process to follow — References files that are not bundled: scripts/rules/*.yaml
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.
- The text references files that are not there: add them or drop the references.
- 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 · 10
✓ No critical or high findings
Medium and low: 10
-
low Dangerous commands
cmd-pipe-to-shellscripts/audit.py:166Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; documentation of a security skill)'curl.*(sh|bash|cmd|powershell)',
code literalsecurity skill -
low Dangerous commands
cmd-pipe-to-shellscripts/audit.py:167Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; documentation of a security skill)'wget.*(sh|bash)',
code literalsecurity skill -
low Dangerous commands
cmd-pipe-to-shellscripts/rules/command_injection.yaml:8Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; documentation of a security skill)- 'curl.*(sh|bash|cmd|powershell)'
code literalsecurity skill -
low Dangerous commands
cmd-pipe-to-shellscripts/rules/command_injection.yaml:9Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; documentation of a security skill)- 'wget.*(sh|bash)'
code literalsecurity skill
A further 6 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 33. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5787 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/rules/*.yaml
Process rating: all ten parameters 33/100
- 0Tools and files. 1 referenced file(s) missing: scripts/rules/*.yaml
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 70Execution cost. Instruction body is 5787 tokens
- 100Steps. 67 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 11 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
- -253 emoji in the instructions: noise for the model
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -32 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 464: enough signal without eating the budget
- +4Structure: 42 headings
- +3Step-by-step instructions: 67 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 47.