SKILLEMALL.ai
GitHub ↗ RU Sign in

CD Li_codeql_LLM

CodeQL 安全扫描与 LLM 智能分析融合工具。自动检测 CodeQL 安装、扫描指定目录、生成漏洞报告、LLM 分析、Jenkins 集成、输出验证 Checklist。

ClawHub Agent Skills author: Terry S Fisher v1.0.0 MIT-0 79 files · 2 scripts body ≈ 1 208 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

TemplateGitHubSoftware developmentAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
64/100
safety, quality, tests
Safety 60%
65
Quality 40%
62
Run on models
none yet
Process rating
D
41/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • 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 · 19

✓ No critical or high findings

Medium and low: 19
  • medium Dangerous commands cmd-shell-rc README_BILINGUAL.md:425
    Writes to a shell startup file
    echo 'export PATH=/opt/codeql/codeql:$PATH' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc README_BILINGUAL.md:451
    Writes to a shell startup file
    echo 'export PATH=/opt/codeql/codeql:$PATH' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc README.md:29
    Writes to a shell startup file
    echo 'export PATH=/opt/codeql/codeql:$PATH' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc README.md:255
    Writes to a shell startup file
    echo 'export PATH=/opt/codeql/codeql:$PATH' >> ~/.bashrc
  • low Exfiltration read-dotenv CONFIG_GUIDE.md:9
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv QUICK_START.md:156
    Reads a .env file
    cat .env | grep -E "JENKINS|CODEQL"
  • low Exfiltration read-dotenv README_FINAL.md:349
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv run.sh:27
    Reads a .env file
    source .env
  • low Exfiltration read-dotenv run.sh:32
    Reads a .env file (quoted — discussed, not commanded)
    echo -e "${BLUE}💡 提示 / Tip: cp .env.example .env${NC}"
    quoted
  • low Exfiltration read-dotenv TEST_REPORT.md:161
    Reads a .env file (test fixture / example file)
    cat .env | grep -E "JENKINS|GITEA|CODEQL"
    fixture
  • low Exfiltration read-dotenv test_scan.sh:41
    Reads a .env file (test fixture / example file; documentation of a security skill)
    source .env 2>/dev/null || true
    fixturesecurity skill
  • low Dangerous commands cmd-eval-dynamic test-20260319-072752/codeql-db/results/run-info-20260318.232800.466.yml:681
    Dynamic code execution from decoded/untrusted input (quoted — discussed, not commanded)
    \ os\n\ndef download(path): \n    os.system(\"wget \" + path) # NOT OK\n\n```\n\
    quoted
  • low Dangerous commands cmd-eval-dynamic test-output/codeql-db/results/run-info-20260318.230324.362.yml:681
    Dynamic code execution from decoded/untrusted input (quoted — discussed, not commanded)
    \ os\n\ndef download(path): \n    os.system(\"wget \" + path) # NOT OK\n\n```\n\
    quoted
  • low Dangerous commands cmd-eval-dynamic test-output2/codeql-db/results/run-info-20260318.230454.430.yml:681
    Dynamic code execution from decoded/untrusted input (quoted — discussed, not commanded)
    \ os\n\ndef download(path): \n    os.system(\"wget \" + path) # NOT OK\n\n```\n\
    quoted
  • low Dangerous commands cmd-eval-dynamic test-output3/codeql-db/results/run-info-20260318.231603.503.yml:681
    Dynamic code execution from decoded/untrusted input (quoted — discussed, not commanded)
    \ os\n\ndef download(path): \n    os.system(\"wget \" + path) # NOT OK\n\n```\n\
    quoted
  • low Exfiltration read-dotenv 配置检查报告.md:150
    Reads a .env file (detector / deny-list definition)
    - ✅ `run.sh` - 使用 `source .env`
    detector
  • low Exfiltration read-dotenv 配置检查报告.md:151
    Reads a .env file (detector / deny-list definition)
    - ✅ `test_scan.sh` - 使用 `source .env`
    detector

A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 79. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 41/100

  • 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
  • 40Consistency. Frontmatter name (Li_codeql_LLM) differs from the folder (li-codeql-llm)
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 100Steps. 47 steps
  • 100Execution cost. Instruction body is 1208 tokens
  • 100Running it twice. No mutating operations
  • 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)
  • +3Description length 88: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -216 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 36 headings
  • +3Step-by-step instructions: 47 items
  • +4Has examples (18 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.

External checks

ClawHub: suspicious
This skill is a security scanner, but it also includes under-scoped Jenkins administration, credential examples, remote analysis paths, and exploit-style validation output that users should review carefully before installing.
LLM: suspicious (high) · VirusTotal: · 29 May 2026