CF ai-career-position
找到你在 AI 时代最值得站的位置。当用户说「评估这个JD」「分析这个职位」「这个岗位怎么样」「这个offer值不值得去」「比较offer」「准备面试」「帮我找方向」「我适合什么方向」「该不该转行」「改简历」「看看我的简历」「识别外包/培训贷」时使用。粘贴一个招聘JD（文本/URL/截图），本地评估匹配度、识破外包与培训贷骗局、对标职级与总包、生成过国内ATS的中文简历、准备面试、追踪投递、比较offer。投递永远由用户自己完成。
找到你在 AI…
As a process F 35/100 · Will not run — References files that are not bundled: templates/*.html
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 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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostinstall.sh:35Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/tanchunzhuo/ai-career-position/main/install.sh | bash
-
medium Dangerous commands
cmd-pipe-to-shellinstall.sh:66Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)# 否则（如 curl | bash 管道执行）下载 tarball 解压到临时目录。
comment -
medium Dangerous commands
cmd-pipe-to-shell-known-hostREADME.md:36Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/tanchunzhuo/ai-career-position/main/install.sh | bash
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostREADME.md:44Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/tanchunzhuo/ai-career-position/main/install.sh | bash -s -- workbuddy
-
medium Obfuscation
obf-hex-escape-chainscripts/bookmarklet.min.txt:1Escaped/char-code string obfuscationjavascript:(function%20()%20%7B%20%22use%20strict%22%3B%20var%20endpoint%20%3D%20%22http%3A%20var%20ti…ors%20%3D%20%5B%20'.name'%2C%20'.job-name'%2C%20'%5Bclass*%3D%22job-name%22%5D%20h1'%2C%2
-
low Dangerous commands
cmd-pipe-to-shell-known-hostinstall.sh:11Pipe-to-shell installer from a well-known host (still executes remote code) (code comment)# curl -fsSL https://raw.githubusercontent.com/tanchunzhuo/ai-career-position/main/install.sh | bash
comment
Files scanned: 47. 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") - warning
missing-refreference to a missing file: templates/*.html
Process rating: all ten parameters 35/100
- 0Tools and files. 1 referenced file(s) missing: templates/*.html
- 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
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 928 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)
- +3Output format is not stated: the model decides each time
- -45 reference files, but SKILL.md never points to them: the model will not open them
- +2Single-language instructions
- +3Description length 217: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (1 code blocks)
- +3All 6 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.