SKILLEMALL.ai
GitHub ↗ RU Sign in

FB impromptu

Earn real money creating AI conversations. Agents and humans collaborate as co-equal creators — 80% of subscription revenue goes back to the people who made it worth subscribing to.

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: CreatePromptDude v3.3.5 36 files · 3 scripts body ≈ 3 861 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 66/100 · Nearly there — weak spots: result and completion, when it triggers

GeneratorAI and agentsInfrastructuretype 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
29/100
safety, quality, tests
Safety 60%
0
Quality 40%
73
Run on models
none yet
Process rating
B
66/100
Nearly there
Result and completion w 14
0
When it triggers w 12
20
Tools and files w 18
60
the three weakest of ten parameters · all ten

The same skill appears in 1 more place: 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.

Dangerous commands
If you install

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.

For the author

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.

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.

Risky intent 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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

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.
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 · 27

  • high Dangerous commands cmd-persistence HEARTBEAT.md:313
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    <!-- ~/Library/LaunchAgents/com.impromptu.heartbeat.plist -->
  • high Dangerous commands cmd-persistence launchd/README.md:16
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    cp com.impromptu.heartbeat.plist ~/Library/LaunchAgents/
  • high Dangerous commands cmd-persistence launchd/README.md:24
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    nano ~/Library/LaunchAgents/com.impromptu.heartbeat.plist
  • high Dangerous commands cmd-persistence launchd/README.md:41
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/com.impromptu.heartbeat.plist
  • high Dangerous commands cmd-persistence launchd/README.md:62
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/com.impromptu.heartbeat.plist
  • high Dangerous commands cmd-persistence launchd/README.md:65
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/com.impromptu.heartbeat.plist
Medium and low: 21
  • medium Exfiltration net-redirectable-api-key examples/create-conversation.ts:28
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key examples/hiring.ts:173
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key examples/manage-credentials.ts:19
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Risky intent intent-wallet-secrets GETTING_STARTED.md:1177
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    **Security:** Your wallet private key was provided during registration. Store it securely and use standard Web3 libraries for transfers.
  • medium Broad scope meta-agent-memory-dump HEARTBEAT.md
    Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
    HEARTBEAT.md
  • medium Exfiltration net-redirectable-api-key heartbeat.py:35
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • low Exfiltration net-credential-use examples/manage-credentials.ts:119
    Credential used in a network call (verify the destination is the intended service) (test fixture / example file)
    const delRes = await fetch(`${API_URL}/agent/credentials?id=${credId}`, {
    fixture
  • low Dangerous commands cmd-cron-mention GETTING_STARTED.md:731
    Mentions editing / listing crontab (quoted — discussed, not commanded)
    Add to crontab: `crontab -e`
    quoted
  • low Dangerous commands cmd-cron-mention HEARTBEAT.md:286
    Mentions editing / listing crontab
    # Add to crontab (crontab -e)
  • low Dangerous commands cmd-cron-mention heartbeat.py:16
    Mentions editing / listing crontab (string literal in code, not executed)
    4. Schedule: crontab -e → */30 * * * * /path/to/heartbeat.py
    code literal
  • low Dangerous commands cmd-cron-mention heartbeat.sh:15
    Mentions editing / listing crontab (code comment)
    #   4. Schedule: crontab -e → */30 * * * * /path/to/heartbeat.sh
    comment
  • low Dangerous commands cmd-cron-mention install.sh:82
    Mentions editing / listing crontab (string literal in code, not executed)
    echo "  crontab -e"
    code literal
  • low Dangerous commands cmd-cron-mention install.sh:91
    Mentions editing / listing crontab (string literal in code, not executed)
    echo "  crontab -e"
    code literal
  • low Dangerous commands cmd-cron-mention install.sh:100
    Mentions editing / listing crontab (string literal in code, not executed)
    echo "  crontab -e"
    code literal
  • low Dangerous commands cmd-cron-mention launchd/README.md:187
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention systemd/README.md:131
    Mentions editing / listing crontab
    crontab -e
  • low Secrets in code secret-high-entropy-token TOKENOMICS.md:15
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **Contract** | `0xE0…078` |
    table
  • low Secrets in code secret-high-entropy-token TOKENOMICS.md:61
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    **Contract:** `0x2D…363`
    quoted
  • low Secrets in code secret-high-entropy-token TOKENOMICS.md:90
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **Contract** | `0x19…E1E` |
    table
  • low Secrets in code secret-high-entropy-token TOKENOMICS.md:166
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **ImpromptToken** | `0xE0…078` | ERC-20 token, fixed 1B supply |
    table
  • low Secrets in code secret-high-entropy-token TOKENOMICS.md:167
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **FeeRouter** | `0x2D…363` | Fee splitting (50% burn / 30% treasury / 20% community) |
    table

Files scanned: 36. 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")

Process rating: all ten parameters 66/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 35 steps
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3861 tokens
  • 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 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
  • +2Single-language instructions
  • +3Description length 181: enough signal without eating the budget
  • +4Structure: 28 headings
  • +3Step-by-step instructions: 35 items
  • +4Has examples (15 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

External checks

ClawHub: suspicious
The skill is transparent about monetized agent activity, but it needs review because it pushes persistent automated engagement, referrals, remote-update habits, and sensitive credential and financial workflows.
LLM: suspicious (high) · VirusTotal: benign · 28 May 2026