SKILLEMALL.ai
GitHub ↗ RU Sign in

DD boss-zhipin-scraper

Scrape BOSS直聘 (job listing site) via Chrome CDP. Searches jobs by keyword/city/filters, fetches JD details, outputs structured JSON/CSV with plaintext salary, and can summarize scraped results into a job-market prompt. Optional --company locally filters results by company name (boss_name substring) with no extra request. Use when user wants to search/analyze jobs on BOSS直聘 or zhipin.com.

Not recommendedcritical or high security findings · low grade D
eatmoreduck/boss-zhipin-scraper Hermes author: eatmoreduck 21 files · 5 scripts body ≈ 2 592 tokens Open the sourcegithub.com↗ analyzed 4 d ago

Scrape BOSS直聘 (job listing site) via Chrome CDP.

As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationData and analyticstype and topics are labelled automatically from the skill text
Runs in: Hermes Agent
JSON
Technical rating
D
68/100
safety, quality, tests
Safety 60%
62
Quality 40%
76
Run on models
none yet
Process rating
D
48/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

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.

Exfiltration
If you install

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".

For the author

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

  1. 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.
  2. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
For the model run — optional
  • 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 · 5

  • high Exfiltration intent-browser-credential-store CHANGELOG.md:74
    Accesses a browser credential / cookie store
    - `--copy-login-state` 手动导入主 Chrome 的 Local State + Cookie 相关文件到隔离 profile
Medium and low: 4
  • medium Exfiltration intent-browser-credential-store README.en.md:195
    Accesses a browser credential / cookie store (documentation table row)
    | `--copy-login-state` | Manually import the main browser's Local State + cookie-related files into the isolated profile (main Chrome for `--setup-chrome`, main Edge for `--setup-edge`; never copied b
    table
  • medium Exfiltration intent-browser-credential-store README.md:197
    Accesses a browser credential / cookie store (documentation table row)
    | `--copy-login-state` | 手动导入主浏览器（`--setup-chrome` 取主 Chrome、`--setup-edge` 取主 Edge）的 Local State + Cookie 相关文件到隔离 profile（默认、首次启动、重复启动都不复制） |
    table
  • medium Exfiltration intent-browser-credential-store SKILL.md:102
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    `--copy-login-state` 在 `--setup-chrome` 下从主 Chrome 导入、在 `--setup-edge` 下从主 Edge 导入，每次运行都会覆盖隔离 profile 内对应的 Cookie 相关文件；日常启动不要加这个参数。它只复制 `Local State` 和 `Default/Cookies*`、`Default/Network/Cookies*` 这类
    quoted
  • medium Exfiltration intent-browser-credential-store SKILL.md:178
    Accesses a browser credential / cookie store (documentation table row)
    | `--copy-login-state` | 关闭 | 手动导入主浏览器（`--setup-chrome` 取主 Chrome、`--setup-edge` 取主 Edge）的 Local State + Cookie 相关文件到隔离 profile；默认、首次启动、重复启动都不复制 |
    table

Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 390 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)

Process rating: all ten parameters 48/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 60Consistency. The Hermes dialect needs category and tags
  • 100Steps. 33 steps
  • 100Execution cost. Instruction body is 2592 tokens
  • 100Running it twice. No mutating operations
  • low 11 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)
  • +3Output format is not stated: the model decides each time
  • -31 of 3 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 390: enough signal without eating the budget
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 33 items
  • +4Has examples (13 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.