SKILLEMALL.ai
GitHub ↗ RU Sign in

CF contextui

Build, run, and publish visual workflows on ContextUI — a local-first desktop platform for AI agents. Create React TSX workflows (dashboards, tools, apps, visualizations), manage local Python backend servers, test workflows via scoped UI automation within the ContextUI app window, and optionally publish to the ContextUI Exchange. All tools operate locally on the user's machine under standard OS permissions — no remote execution or privilege escalation. Python backends bind to localhost. See SECURITY.md for the full capability scope and trust model. Requires ContextUI installed locally and MCP server configured.

ClawHub Agent Skills author: Midz99 v1.0.7 14 files · 1 script body ≈ 4 289 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 45/100 · Will not run — References files that are not bundled: examples/KokoroTTS/ui/ServerLauncher/, examples/KokoroTTS/

ProcedureSoftware developmentAI and agentstype 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
C
66/100
safety, quality, tests
Safety 60%
68
Quality 40%
63
Run on models
none yet
Process rating
F
45/100
Will not run
References files that are not bundled: examples/KokoroTTS/ui/ServerLauncher/, examples/KokoroTTS/
Tools and files w 18
0
Result and completion w 14
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
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 · 12

✓ No critical or high findings

Medium and low: 12
  • medium Exfiltration net-credential-use scripts/exchange.sh:28
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $KEY" "$BASE/marketplace?search=$(echo "${@:2}" | sed 's/ /%20/g')"
  • medium Exfiltration net-credential-use scripts/exchange.sh:32
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $KEY" "$BASE/marketplace?id=$2"
  • medium Exfiltration net-credential-use scripts/exchange.sh:36
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $KEY" "$BASE/marketplace?category=$2"
  • medium Exfiltration net-credential-use scripts/exchange.sh:40
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $KEY" "$BASE/marketplace-download?id=$2"
  • medium Exfiltration net-credential-use scripts/exchange.sh:44
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $KEY" "$BASE/marketplace-comments?listingId=$2"
  • low Exfiltration net-credential-use references/exchange-api.md:55
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -H "Authorization: Bearer $CONTEXTUI_API_KEY" \
    security skill
  • low Exfiltration net-credential-use references/exchange-api.md:59
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -H "Authorization: Bearer $CONTEXTUI_API_KEY" \
    security skill
  • low Exfiltration net-credential-use references/exchange-api.md:63
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -H "Authorization: Bearer $CONTEXTUI_API_KEY" \
    security skill
  • low Exfiltration net-credential-use references/exchange-api.md:72
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -H "Authorization: Bearer $CONTEXTUI_API_KEY" \
    security skill
  • low Exfiltration net-credential-use references/exchange-api.md:82
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -H "Authorization: Bearer $CONTEXTUI_API_KEY" \
    security skill
  • low Risky intent intent-offensive-security SECURITY.md:57
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    No tool in this skill requires or requests elevated permissions (sudo, admin). All operations run as the current OS user with no privilege escalation.
  • low Risky intent intent-offensive-security SKILL.md:3
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    description: Build, run, and publish visual workflows on ContextUI — a local-first desktop platform for AI agents. Create React TSX workflows (dashboards, tools, apps, visualizations), manage local Py
    quoted

Files scanned: 14. 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 missing-ref reference to a missing file: examples/KokoroTTS/ui/ServerLauncher/
  • warning missing-ref reference to a missing file: examples/KokoroTTS/
  • note frontmatter-key unknown frontmatter key "source"
  • note frontmatter-key unknown frontmatter key "youtube"
  • note frontmatter-key unknown frontmatter key "env"

Process rating: all ten parameters 45/100

Will not run. References files that are not bundled: examples/KokoroTTS/ui/ServerLauncher/, examples/KokoroTTS/
  • 0Tools and files. 2 referenced file(s) missing: examples/KokoroTTS/ui/ServerLauncher/, examples/KokoroTTS/
  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 7 mutating operations with no state check
  • 60Failures and branches. 2 branches
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 4289 tokens
  • 100Steps. 55 steps
  • 100Consistency. Name and required fields are in place
  • low 10 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
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • +1No license
  • +2Single-language instructions
  • +3Description length 618: enough signal without eating the budget
  • +4Structure: 42 headings
  • +3Step-by-step instructions: 55 items
  • +4Has examples (15 code blocks)
  • +4Reference files are cited in the instructions (6 of 7)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.

External checks

ClawHub: suspicious
This skill is mostly a coherent ContextUI workflow toolkit, but it includes high-impact marketplace, local execution, and persisted MCP capabilities with several under-scoped safety gaps users should review before installing.
LLM: suspicious (high) · VirusTotal: suspicious · 10 Sept 2026