SKILLEMALL.ai
GitHub ↗ RU Sign in

FB redbook

Search, read, analyze, and automate Xiaohongshu (小红书) content via CLI

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: saybanet v0.5.0 MIT-0 22 files body ≈ 8 860 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process B 73/100 · Nearly there — weak spots: when it triggers, consistency, execution cost

IntegrationInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
F
22/100
safety, quality, tests
Safety 60%
0
Quality 40%
55
Run on models
none yet
Process rating
B
73/100
Nearly there
When it triggers w 12
20
Consistency w 8
40
Execution cost w 6
40
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: redbook (ClawHub)

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.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 26

  • high Exfiltration intent-browser-credential-store CLAUDE.md:42
    Accesses a browser credential / cookie store
    - Auto-discovers Chrome profiles via `~/Library/Application Support/Google/Chrome/Local State`
  • high Exfiltration intent-browser-credential-store README.md:277
    Accesses a browser credential / cookie store
    const cookies = await loadCookies("chrome");
  • high Exfiltration intent-browser-credential-store README.md:326
    Accesses a browser credential / cookie store
    Requires Node.js >= 22. Supports **macOS, Windows, and Linux**. Uses cookies from your Chrome browser session — you must be logged into xiaohongshu.com in Chrome.
  • high Exfiltration intent-browser-credential-store README.md:331
    Accesses a browser credential / cookie store
    - **Windows** — Chrome 127+ uses App-Bound Encryption. The CLI auto-launches Chrome headless to read cookies (close Chrome first). If auto-extraction fails, use `--cookie-string` as fallback
  • high Exfiltration intent-browser-credential-store SKILL.md:959
    Accesses a browser credential / cookie store
    const cookies = await loadCookies("chrome");
  • high Exfiltration intent-browser-credential-store src/cli.ts:84
    Accesses a browser credential / cookie store
    const cookies = await extractCookies(cookieSource as CookieSource, chromeProfile);
Medium and low: 20
  • medium Exfiltration intent-browser-credential-store CLAUDE.md:22
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    - `src/lib/cookies.ts` — Cookie extraction with Chrome profile auto-discovery
    quoted
  • medium Exfiltration intent-browser-credential-store README.md:135
    Accesses a browser credential / cookie store (documentation table row)
    | `--cookie-string <cookies>` | 手动传入 Cookie 字符串：`"a1=值; web_session=值"`（从 Chrome DevTools 复制） | 无 |
    table
  • medium Exfiltration intent-browser-credential-store README.md:432
    Accesses a browser credential / cookie store (detector / deny-list definition)
    | `--cookie-source <browser>` | Browser to read cookies from (chrome, safari, firefox) | `chrome` |
    detector
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Write Glob Grep
  • medium Exfiltration intent-browser-credential-store src/cli.ts:54
    Accesses a browser credential / cookie store (detector / deny-list definition)
    "Browser to read cookies from (chrome, safari, firefox)",
    detector
  • medium Exfiltration intent-browser-credential-store src/lib/cdp-cookies.ts:6
    Accesses a browser credential / cookie store (code comment)
    * Chrome via its DevTools Protocol to read cookies directly — Chrome
    comment
  • medium Exfiltration intent-browser-credential-store src/lib/cdp-cookies.ts:252
    Accesses a browser credential / cookie store (code comment)
    // Copy Cookies database + journal/WAL files (older Chrome path)
    comment
  • medium Exfiltration intent-browser-credential-store src/lib/cdp-cookies.ts:257
    Accesses a browser credential / cookie store (code comment)
    // Copy Network/Cookies (newer Chrome versions store cookies here)
    comment
  • medium Exfiltration intent-browser-credential-store src/lib/cdp-cookies.ts:287
    Accesses a browser credential / cookie store (code comment)
    * Attempt to extract XHS cookies via Chrome DevTools Protocol.
    comment
  • medium Exfiltration intent-browser-credential-store src/lib/cookies.ts:44
    Accesses a browser credential / cookie store (code comment)
    * Resolve the Chrome "Local State" file path for the current platform.
    comment
  • medium Exfiltration intent-browser-credential-store src/lib/cookies.ts:60
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    return join(localAppData, "Google", "Chrome", "User Data", "Local State");
    quoted
  • medium Exfiltration intent-browser-credential-store src/lib/cookies.ts:63
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    return join(homedir(), ".config", "google-chrome", "Local State");
    quoted
  • medium Exfiltration intent-browser-credential-store src/lib/cookies.ts:69
    Accesses a browser credential / cookie store (code comment)
    * Discover Chrome profiles from Local State file.
    comment
  • medium Exfiltration intent-browser-credential-store src/lib/cookies.ts:220
    Accesses a browser credential / cookie store (detector / deny-list definition)
    log(`Reading cookies from ${source}${chromeProfile ? ` (profile: ${chromeProfile})` : ""}...`);
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:83
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…asG+Fkr6…2vM+P9eO…k5W+1WL8w==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:93
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…bKX+KS9G…yMA/NhKJ…RGz/Q==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:153
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…Wwy+ghLE…vfU/YnxW…fdg==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:208
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…g8l+lMts…kjn+hp+Yv3g==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:261
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…2BV+FY5ZFezP/ypmwayk68+NzzA…NFD/uUmBJuGoXw==",
    detector
  • low Dangerous commands cmd-privilege src/lib/render.ts:598
    Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)
    args: ["--no-sandbox", "--disable-setuid-sandbox", "--disable-gpu"],
    detectorcode literal

Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 8860 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 73/100

  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (redbook) differs from the folder (sayba-redbook)
  • 40Execution cost. Instruction body is 8860 tokens: crowds the task out of the window
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 165 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 12 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (42 tags): a typed call is more reliable

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 69: 120–800 characters recommended
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • -32 of 2 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Structure: 66 headings
  • +3Step-by-step instructions: 165 items
  • +3Output format is stated explicitly
  • +4Has examples (34 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.

External checks

ClawHub: suspicious
This is a disclosed Xiaohongshu automation tool, but it needs Review because it automatically accesses browser session cookies, persists itself into Claude, and can perform real account actions.
LLM: suspicious (high) · VirusTotal: · 29 May 2026