SKILLEMALL.ai
GitHub ↗ RU Sign in

DC last30days

Recent community and social trend research over the last 30 days. Use when the brief asks what people are saying now, recent sentiment, community reactions, social proof, launch reaction, trend scan, or last-30-days context.

nexu-io/open-design Agent Skills author: nexu-io Apache-2.0 75 files · 68 scripts body ≈ 1 150 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Recent community and social trend research over the last 30 days.

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureData and analyticsWriting and documentstype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
D
61/100
safety, quality, tests
Safety 60%
46
Quality 40%
84
Run on models
none yet
Process rating
C
53/100
Has gaps
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
This is a copy of a skill from another catalog; the rating counts the canonical one: last30days (nexu-io/open-design)

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration 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 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

    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 · 14

    ✓ No critical or high findings

    Medium and low: 14
    • medium Exfiltration intent-browser-credential-store scripts/lib/chrome_cookies.py:3
      Accesses a browser credential / cookie store (quoted — discussed, not commanded)
      Extracts cookies from Chrome's encrypted SQLite database using only stdlib
      quoted
    • medium Exfiltration intent-browser-credential-store scripts/lib/chrome_cookies.py:169
      Accesses a browser credential / cookie store (quoted — discussed, not commanded)
      """Extract cookies from Chrome on macOS.
      quoted
    • medium Exfiltration intent-browser-credential-store scripts/lib/chrome_cookies.py:183
      Accesses a browser credential / cookie store (quoted — discussed, not commanded)
      logger.info("Chrome cookies database not found at %s", CHROME_COOKIES_DB)
      quoted
    • medium Exfiltration intent-browser-credential-store scripts/lib/chrome_cookies.py:250
      Accesses a browser credential / cookie store (detector / deny-list definition)
      logger.info("No matching cookies found in Chrome for domain %s", domain)
      detector
    • medium Exfiltration intent-browser-credential-store scripts/lib/cookie_extract.py:3
      Accesses a browser credential / cookie store (quoted — discussed, not commanded)
      Extracts cookies from local browser databases (Firefox, Chrome, Safari)
      quoted
    • medium Exfiltration intent-browser-credential-store scripts/lib/cookie_extract.py:125
      Accesses a browser credential / cookie store (quoted — discussed, not commanded)
      """Find the first directory that contains cookies.sqlite."""
      quoted
    • medium Exfiltration intent-browser-credential-store scripts/lib/cookie_extract.py:128
      Accesses a browser credential / cookie store (quoted — discussed, not commanded)
      if child.is_dir() and (child / "cookies.sqlite").is_file():
      quoted
    • medium Exfiltration intent-browser-credential-store scripts/lib/cookie_extract.py:140
      Accesses a browser credential / cookie store (quoted — discussed, not commanded)
      Firefox locks cookies.sqlite while running, so we copy first.
      quoted
    • medium Exfiltration intent-browser-credential-store scripts/lib/cookie_extract.py:197
      Accesses a browser credential / cookie store (quoted — discussed, not commanded)
      return _query_cookies_db(profile_path / "cookies.sqlite", domain, cookie_names)
      quoted
    • medium Exfiltration intent-browser-credential-store scripts/lib/vendor/bird-search/lib/cookies.js:113
      Accesses a browser credential / cookie store (detector / deny-list definition)
      warnings.push('No Twitter cookies found in Chrome. Make sure you are logged into x.com in Chrome.');
      detector
    • low Dangerous commands cmd-background-process scripts/lib/subproc.py:4
      Starts a background / autostarted process (string literal in code, not executed)
      and transcript download). Both need the same os.setsid/killpg cleanup
      code literal
    • low Dangerous commands cmd-background-process scripts/lib/subproc.py:39
      Starts a background / autostarted process (string literal in code, not executed)
      Spawns ``cmd`` inside its own process group via ``os.setsid`` where
      code literal
    • low Dangerous commands cmd-background-process scripts/lib/subproc.py:61
      Starts a background / autostarted process
      preexec = os.setsid if hasattr(os, "setsid") else None
    • low Secrets in code secret-high-entropy-token scripts/lib/vendor/bird-search/lib/twitter-client-base.js:88
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      authorization: 'Bearer AAAA…uTs%3D1Z…TnA',
      quoted

    Files scanned: 75. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "triggers"
    • note frontmatter-key unknown frontmatter key "od"

    Process rating: all ten parameters 53/100

    • 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
    • 30Running it twice. 1 mutating operations with no state check
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 100Steps. 18 steps
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1150 tokens
    • low The response is described with custom markup (3 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)
    • +3Output format is not stated: the model decides each time
    • -33 of 4 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +3Description length 224: enough signal without eating the budget
    • +4Structure: 6 headings
    • +3Step-by-step instructions: 18 items
    • +4Has examples (3 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.