SKILLEMALL.ai
GitHub ↗ RU Sign in

FD A 股每日精选技能

每日获取 A 股新股发行信息和 20 元以下的精选股票，通过邮件发送给用户。

Not recommendedcritical or high security findings · low grade F
modbender/skill-library-mcp Agent Skills author: modbender MIT 19 files · 4 scripts body ≈ 118 tokens Open the sourcegithub.com↗ analyzed 3 d ago

每日获取 A 股新股发行信息和 20 元以下的精选股票，通过邮件发送给用户。

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

Proceduretype 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
F
22/100
safety, quality, tests
Safety 60%
0
Quality 40%
56
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
When it triggers w 12
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
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. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. 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 · 30

  • high Dangerous commands cmd-persistence setup-cron.sh:8
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    CURRENT_CRON=$(crontab -l 2>/dev/null || echo "")
  • high Dangerous commands cmd-persistence setup-cron.sh:31
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (echo "$CURRENT_CRON"; echo "$CRON_LINE") | crontab -
  • high Dangerous commands cmd-persistence setup.sh:133
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    (crontab -l 2>/dev/null | grep -v "astock-daily"; echo "$CRON_LINE") | crontab -
Medium and low: 27
  • medium Dangerous commands cmd-privilege DNS-FIX.md:31
    Privilege escalation / world-writable permissions
    sudo sh -c 'echo "47.246.165.89 smtp.qiye.aliyun.com" >> /etc/hosts'
  • medium Dangerous commands cmd-privilege DNS-FIX.md:32
    Privilege escalation / world-writable permissions
    sudo sh -c 'echo "47.246.165.89 smtp.mxhichina.com" >> /etc/hosts'
  • medium Dangerous commands cmd-privilege fix-hosts.sh:12
    Privilege escalation / world-writable permissions
    sudo sh -c 'echo "47.246.165.89 smtp.qiye.aliyun.com" >> /etc/hosts'
  • medium Dangerous commands cmd-privilege fix-hosts.sh:20
    Privilege escalation / world-writable permissions
    sudo sh -c 'echo "47.246.165.89 smtp.mxhichina.com" >> /etc/hosts'
  • medium Dangerous commands cmd-persistence setup-cron.sh:23
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)
    echo "$CURRENT_CRON" | grep -v "astock-daily" | crontab -
    detector
  • low Dangerous commands cmd-cron-mention CONFIG.md:39
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention CONFIG.md:62
    Mentions editing / listing crontab
    crontab -l
  • low Exfiltration read-dotenv CONFIG.md:81
    Reads a .env file
    source .env && node index.js
  • low Dangerous commands cmd-cron-mention CONFIG.md:168
    Mentions editing / listing crontab
    crontab -e
  • low Exfiltration read-dotenv CONFIG.md:190
    Reads a .env file
    source .env && node index.js
  • low Dangerous commands cmd-cron-mention cron-example.sh:6
    Mentions editing / listing crontab (code comment; test fixture / example file)
    # crontab -e
    commentfixture
  • low Exfiltration read-dotenv CRON-JOB.md:98
    Reads a .env file (detector / deny-list definition)
    --message "cd /Users/batype/.openclaw/workspace-work/skills/astock-daily && source .env && node index.js" \
    detector
  • low Exfiltration read-dotenv DNS-FIX.md:74
    Reads a .env file
    source .env && node index.js
  • low Exfiltration read-dotenv fix-hosts.sh:35
    Reads a .env file (detector / deny-list definition)
    echo "   source .env && node index.js"
    detector
  • low Exfiltration read-dotenv QUICKSTART.md:24
    Reads a .env file
    source .env && node index.js
  • low Dangerous commands cmd-cron-mention QUICKSTART.md:34
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention README.md:48
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention README.md:83
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention setup-cron.sh:8
    Mentions editing / listing crontab
    CURRENT_CRON=$(crontab -l 2>/dev/null || echo "")
  • low Exfiltration read-dotenv setup-cron.sh:28
    Reads a .env file (detector / deny-list definition)
    CRON_LINE="30 9 * * 1-5 cd $SCRIPT_DIR && source .env && /opt/homebrew/bin/node index.js >> /tmp/astock-daily.log 2>&1"
    detector
  • low Dangerous commands cmd-cron-mention setup-cron.sh:37
    Mentions editing / listing crontab
    crontab -l
  • low Dangerous commands cmd-cron-mention setup-cron.sh:45
    Mentions editing / listing crontab (string literal in code, not executed)
    echo "   查看任务：crontab -l"
    code literal
  • low Dangerous commands cmd-cron-mention setup-cron.sh:46
    Mentions editing / listing crontab (string literal in code, not executed)
    echo "   删除任务：crontab -e (手动删除对应行)"
    code literal
  • low Dangerous commands cmd-cron-mention setup.sh:130
    Mentions editing / listing crontab
    if crontab -l 2>/dev/null | grep -q "astock-daily"; then
  • low Dangerous commands cmd-cron-mention setup.sh:133
    Mentions editing / listing crontab
    (crontab -l 2>/dev/null | grep -v "astock-daily"; echo "$CRON_LINE") | crontab -
  • low Dangerous commands cmd-cron-mention setup.sh:139
    Mentions editing / listing crontab (string literal in code, not executed)
    echo "💡 查看 cron: crontab -l"
    code literal
  • low Exfiltration read-dotenv setup.sh:148
    Reads a .env file (detector / deny-list definition)
    echo "   source .env && node index.js"
    detector

Files scanned: 19. 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-short description under 40 chars: too little signal for triggering
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 46/100

  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 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
  • 40Consistency. Frontmatter name (A 股每日精选技能) differs from the folder (astock-daily)
  • 100Tools and files. No external tools needed
  • 100Steps. 4 steps
  • 100Execution cost. Instruction body is 118 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 38: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 9 headings
  • +3Step-by-step instructions: 4 items
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.