BD vision
让没有原生 vision 能力的模型获得识图能力。当用户发送图片、分享图片路径、或要求分析/描述/识别图片内容时，必须使用此 skill。 触发场景（必须使用）：用户说"看这张图"、"帮我识别这个图片"、"描述一下这张图"、"分析这个截图"、"比较这些图片"、发送图片文件路径、消息中出现图片附件、或要求识别图片中的文字/内容时。 多图支持：当用户一次发送多张图片或要求比较/对比图片时，使用多图模式。 不触发场景：用户只是讨论图片处理技术、询问图片格式、要求生成图片、或编写图片处理代码时，不要使用此 skill。
As a process D 49/100 · 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 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.
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.
- 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 Dangerous commands
cmd-pipe-to-shellinstall.sh:31Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)echo "用法：curl -fsSL https://.../install.sh | bash"
code literal -
medium Exfiltration
net-redirectable-api-keyscripts/vision.js:48Helper 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
Files scanned: 6. 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")
Process rating: all ten parameters 49/100
- 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
- 40Consistency. Frontmatter name (vision) differs from the folder (vision-2)
- 100Tools and files. No external tools needed
- 100Steps. 6 steps
- 100Execution cost. Instruction body is 316 tokens
- 100Running it twice. No mutating operations
- medium 5 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 258: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (6 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.