CF 秒应
创建在线表单收集信息、制作调查问卷、发起投票活动、预约报名、数据查询表格或截图收集任务。支持打卡签到、接龙报名、在线考试、选课抢课、时段预约、信息查询等场景。当用户需要制作问卷、收集报名信息、进行投票选举、预约时间段、创建查询表格或收集图片截图时使用此技能。
As a process F 26/100 · Will not run — References files that are not bundled: /完整/路径/qrcodes/tongji_XXX.jpeg, /Users/用户名/Desktop/miaoying_login.png
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.
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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Exfiltration
net-credential-useSKILL.md:194Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $MIAOYING_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:211Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $MIAOYING_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:637Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $MIAOYING_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:641Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $MIAOYING_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:645Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $MIAOYING_API_KEY" \
Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5662 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: /完整/路径/qrcodes/tongji_XXX.jpeg - warning
missing-refreference to a missing file: /Users/用户名/Desktop/miaoying_login.png - note
frontmatter-keyunknown frontmatter key "install" - note
frontmatter-keyunknown frontmatter key "credentials" - note
frontmatter-keyunknown frontmatter key "env" - note
frontmatter-keyunknown frontmatter key "binaries" - note
frontmatter-keyunknown frontmatter key "file_access" - note
frontmatter-keyunknown frontmatter key "network"
Process rating: all ten parameters 26/100
- 0Tools and files. 2 referenced file(s) missing: /完整/路径/qrcodes/tongji_XXX.jpeg, /Users/用户名/Desktop/miaoying_login.png
- 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
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (秒应) differs from the folder (miaoying)
- 70Execution cost. Instruction body is 5662 tokens
- 100Steps. 128 steps
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (7 tags): a typed call is more reliable
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
- -243 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 129: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 128 items
- +4Has examples (50 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 43.