SKILLEMALL.ai
RU Sign in

DF Li_python_sec_check

Python 安全规范检查工具 - 基于 CloudBase 规范 + 腾讯安全指南 + LLM 智能分析（LLM 功能默认禁用，本地执行优先）

Not recommendedlow grade D
ClawHub Hermes author: Terry S Fisher v0.0.2 MIT-0 27 files · 1 script body ≈ 0 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process F 34/100 · Will not run — weak spots: steps, result and completion, when it triggers

ProcedureAI and agentsSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
D
49/100
safety, quality, tests
Safety 60%
82
Quality 40%
0
Run on models
none yet
Process rating
F
34/100
Will not run
Steps w 15
0
Result and completion w 14
0
Inputs and preconditions w 11
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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.
  2. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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 · 6

✓ No critical or high findings

Medium and low: 6
  • medium Exfiltration net-redirectable-api-key scripts/llm_analyzer.py:29
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Dangerous commands cmd-eval-dynamic test-reports-v21/bandit-report.html:200
    Dynamic code execution from decoded/untrusted input
    30	    os.system("ping -c 1 " + host)
  • medium Dangerous commands cmd-eval-dynamic test-reports/bandit-report.html:200
    Dynamic code execution from decoded/untrusted input
    30	    os.system("ping -c 1 " + host)
  • low Exfiltration read-dotenv docs/目录扫描功能验证.md:314
    Reads a .env file
    cp .env.example .env
  • low Secrets in code secret-password-literal examples/unsafe-example/app.py:13
    Hard-coded password / key literal (may be an example) (placeholder value)
    API_KEY = "sk-1…def"
    placeholder
  • low Dangerous commands cmd-eval-dynamic examples/unsafe-example/app.py:30
    Dynamic code execution from decoded/untrusted input (test fixture / example file)
    os.system("ping -c 1 " + host)
    fixture

Files scanned: 27. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error body-empty SKILL.md: empty instructions body
  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-long-hermes description is 72 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill

Process rating: all ten parameters 34/100

  • 0Steps. Prose only: no discrete steps
  • 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_python_sec_check) differs from the folder (li-python-sec-check)
  • 100Tools and files. No external tools needed
  • 100Execution cost. Instruction body is 0 tokens
  • 100Running it twice. No mutating operations

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 72: 120–800 characters recommended
  • +4Structure: 0 headings, hard to scan
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • -15SKILL.md body under 300 characters: nearly empty
  • -47 reference files, but SKILL.md never points to them: the model will not open them
  • -32 of 2 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.

External checks

ClawHub: clean
This is a disclosed local Python security-checking skill with optional LLM analysis, but users should avoid running the intentionally unsafe example app as a server.
LLM: benign (high) · VirusTotal: · 29 May 2026