CD 狐表(Foxtable) 移动端开发
狐表(Foxtable)移动端开发完整文档，涵盖HTML入门、WeUI框架、微信接口、客户端类、JSON解析、异步编程、Web数据源等，完整保留多层导航结构
狐表(Foxtable)移动端开发完整文档，涵盖HTML入门、WeUI框架、微信接口、客户端类、JSON解析、异步编程、Web数据源等，完整保留多层导航结构
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 13
-
high Exfiltration
intent-browser-credential-storeskill-card.md:14Accesses a browser credential / cookie storeDevelopers and agents use this skill to answer questions and produce implementation guidance for Foxtable mobile and Web development. It is most relevant for Foxtable projects involving WeUI pages, We
Medium and low: 12
-
medium Obfuscation
obf-base64-blobreferences/09_微信接口.md:4769Long base64-looking blobgQGj…QEA
-
low Obfuscation
obf-base64-blobreferences/07_客户端类.md:729Long base64-looking blob (quoted — discussed, not commanded)"1GDE…07A"
quoted -
low Obfuscation
obf-base64-blobreferences/07_客户端类.md:902Long base64-looking blob (quoted — discussed, not commanded)"1GDE…07A"
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/09_微信接口.md:883High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)= "eHDd…z0k"
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/09_微信接口.md:944High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)= "eHDd…NoQ"
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/09_微信接口.md:1005High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)= "eHDd…oLM"
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/09_微信接口.md:1044High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)= "ofjt…fBI"
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/09_微信接口.md:1088High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)= "ofjt…fBI"
quoted -
low Obfuscation
obf-base64-blobreferences/09_微信接口.md:4781Long base64-looking blob (quoted — discussed, not commanded)"gQGj…QEA"
quoted -
low Obfuscation
obf-base64-blobreferences/09_微信接口.md:7211Long base64-looking blob (quoted — discussed, not commanded)"2UgI…8bg"
quoted -
low Obfuscation
obf-base64-blobreferences/09_微信接口.md:7633Long base64-looking blob (quoted — discussed, not commanded)"2UgI…8bg"
quoted -
low Obfuscation
obf-base64-blobreferences/09_微信接口.md:8822Long base64-looking blob (quoted — discussed, not commanded)"1GDE…07A"
quoted
Files scanned: 19. 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 "read_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 (狐表(Foxtable) 移动端开发) differs from the folder (foxmobile-dev-doc)
- 100Tools and files. No external tools needed
- 100Steps. 4 steps
- 100Execution cost. Instruction body is 414 tokens
- 100Running it twice. No mutating operations
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 78: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 5 headings
- +3Step-by-step instructions: 4 items
- +4Reference files are cited in the instructions (17 of 17)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.