CF jdgold
京东黄金ToC智能助手：实时金价查询（京东24h/上金所/伦敦金/7家银行积存金）、持仓收益与诊断、交易记录与条件单、黄金综合分析、贵金属行情与K线、资讯快讯、大V排行、黄金模拟交易（模拟买卖与全自动托管盯盘）。
京东黄金ToC智能助手：实时金价查询（京东24h/上金所/伦敦金/7家银行积存金）、持仓收益与诊断、交易记录与条件单、黄金综合分析、贵金属行情与K线、资讯快讯、大V排行、黄金模拟交易（模拟买卖与全自动托管盯盘）。
As a process F 34/100 · Will not run — References files that are not bundled: 链接, ...
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 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".
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Exfiltration
net-redirectable-api-keyscripts/jdjr_config.py:86Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Dangerous commands
cmd-persistencescripts/sim_autotrade.py:454Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)notify("黄金托管启动失败", r.stderr.strip() or "launchctl load 失败")code literal -
medium Dangerous commands
cmd-persistencescripts/sim_autotrade.py:455Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)log(f"launchctl load 失败：{r.stderr.strip()}", level="ERROR")code literal -
medium Dangerous commands
cmd-persistenceSKILL.md:368Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)3. **部署 launchd 定时任务**：执行 `python3 scripts/sim_autotrade.py --claw <客户端> --install-launchd`（可选加 `--daily-cap <数值>` 设单日上限）。脚本会**自动**读取模板、替换占位符 `__CLAW__` / `__PROJECT_DIR__` / `__PYTHON__`、生成 plist 到 `
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/jdjr_config.py:34High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)DEFAULT_CLAWX_JR_API_KEY = "claw…scT"
quoted -
low Dangerous commands
cmd-persistencescripts/sim_autotrade.py:53Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)f"~/Library/LaunchAgents/{PLIST_LABEL}.plist")detectorcode literal -
low Dangerous commands
cmd-persistencescripts/sim_autotrade.py:411Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; string literal in code, not executed)- 写入 ~/Library/LaunchAgents/ 后 launchctl load。
detectorcode literal
Files scanned: 37. 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 ≈ 6229 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: 链接 - warning
missing-refreference to a missing file: ...
Process rating: all ten parameters 34/100
- 0Tools and files. 2 referenced file(s) missing: 链接, ...
- 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
- 70Execution cost. Instruction body is 6229 tokens
- 100Steps. 195 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 13 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 106: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -245 emoji in the instructions: noise for the model
- -312 of 21 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 57 headings
- +3Step-by-step instructions: 195 items
- +4Has examples (13 code blocks)
- +4Reference files are cited in the instructions (12 of 12)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.