BD video_notification
向指定手机号发送视频通知（基于 IVVR 平台）。需要提供服务器上已存在的视频文件绝对路径，文件大小不超过 5MB。
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Exfiltration
exfil-webhook-urlSKILL.md:73Webhook / callback URL commonly used for exfiltration (verify the destination) (security demo / example)description: 视频通知服务的公网地址（例如 https://your-domain.com 或 http://xxx.ngrok.io），注意不要带尾部斜杠
demo -
low Exfiltration
exfil-webhook-urlSKILL.md:14Webhook / callback URL commonly used for exfiltration (verify the destination) (code comment; security demo / example)base_url: "{{API_BASE_URL}}" # 用户需在环境变量中设置，例如 https://your-domain.com 或 http://xxx.ngrok.iocommentdemo
Files scanned: 2. 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") - note
frontmatter-keyunknown frontmatter key "icon" - note
frontmatter-keyunknown frontmatter key "endpoint" - note
frontmatter-keyunknown frontmatter key "input_schema" - note
frontmatter-keyunknown frontmatter key "output_schema" - note
frontmatter-keyunknown frontmatter key "examples" - note
frontmatter-keyunknown frontmatter key "env_vars"
Process rating: all ten parameters 46/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (video_notification) differs from the folder (video-notification)
- 100Tools and files. No external tools needed
- 100Steps. 9 steps
- 100Execution cost. Instruction body is 135 tokens
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 58: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -4Absolute local paths (C:\Users, /home/…): not portable
- +2Single-language instructions
- +4Structure: 5 headings
- +3Step-by-step instructions: 9 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.