BD phone-detection-alert
玩手机检测告警技能。通过摄像头抓图→AI 分析→TTS 语音→设备播放的完整流程。Use when: 需要监控玩手机行为并自动告警、课堂/考场/会议室纪律监控、通过萤石摄像头进行 AI 行为检测。
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 files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
How to improve
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Secrets in code
secret-labelled-tokenreferences/ezviz-api-docs.md:54Labelled token / key literal (vendor format unknown — verify it is not a live credential)appKey=9mqi…srl&appSecret=096e…776
-
low Secrets in code
secret-password-literalreferences/ezviz-api-docs.md:138Hard-coded password / key literal (may be an example)accessToken=at.1…929&deviceSerial=427734888&channelNo=1
-
low Secrets in code
secret-password-literalreferences/ezviz-api-docs.md:227Hard-coded password / key literal (may be an example) (detector / deny-list definition)--header 'accessToken: at.3…rfi' \
detector
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: 玩手机检测告警技能。通过摄像头抓图→AI 分析→TTS 语音→设备播放的完整流程。Use when: 需要监控玩手机行为并自动告警、… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
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 (phone-detection-alert) differs from the folder (ezviz-open-capture)
- 100Tools and files. No external tools needed
- 100Steps. 52 steps
- 100Execution cost. Instruction body is 1323 tokens
- low 10 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 98: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -230 emoji in the instructions: noise for the model
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +4Structure: 13 headings
- +3Step-by-step instructions: 52 items
- +4Has examples (8 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.