Skills/ClawHub/impromptu

impromptu@3.3.5

CAUTION· install only

Publisher claims: "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..." Observed in sandbox: calls impromptusocial.ai only, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher createpromptdude · publishing for 274 daysInstalls 1,766Last detonated 39 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 3 of 3 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Direct script execution from GitHub raw URL; Direct script execution from GitHub raw URL. Summary: calls impromptusocial.ai only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 5 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.0sprocessexec /usr/bin/mkdir
0.0sprocessbundled script run in the sandbox with no arguments
0.1sfilesystemwrote ~/.impromptu/heartbeat.log
0.1sprocessexited 1:
0.1sprocessbundled script run in the sandbox with no arguments
0.2sfilesystemwrote ~/.impromptu/heartbeat.log
0.2sprocessexec /usr/bin/mkdir
0.2sprocessexec /usr/bin/tee
0.2sprocessexited 1:
0.2sprocessbundled script run in the sandbox with no arguments
4.7sfilesystemread ~/ldaprc · ~/.ldaprc outside project
4.7snetworkCONNECT tcp://impromptusocial.ai:443
4.7sprocessexec /usr/bin/curl
4.7sprocessexec /usr/bin/head
4.7sprocessexec /usr/bin/cut
4.7sprocessexited 1:
4.7sprocess3 of 3 bundled scripts run with no arguments
4.7sprocessscript backend runs setup only
4.7sprocessscript backend runs setup only
4.7sprocesssecond launch, clock +45 days, CI unset
4.8sprocessexec /usr/bin/mkdir

Static findings

HIGH
Direct script execution from GitHub raw URLimpromptu.skill.json:2056 · Direct script execution from GitHub raw URL — unverified code source"python": "https://raw.githubusercontent.com/impromptu/openclaw-skill/main/heartbeat.py",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Direct script execution from GitHub raw URLimpromptu.skill.json:2055 · Direct script execution from GitHub raw URL — unverified code source"bash": "https://raw.githubusercontent.com/impromptu/openclaw-skill/main/heartbeat.sh",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Authorization escalation languageSECURITY.md:313 · Authorization escalation language · informational: not an instruction filescopes: ['read'] // No write or admin accessFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandheartbeat.sh:12 · File permission modification command — agent changes file ownership/permissions# 1. chmod +x heartbeat.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandimpromptu-health.sh:9 · File permission modification command — agent changes file ownership/permissions# chmod +x impromptu-health.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandheartbeat.py:13 · File permission modification command — agent changes file ownership/permissions1. chmod +x heartbeat.pyFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈4,143 tok
1 file · 36 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim createpromptdude: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  3. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim createpromptdudePropose a patch to the maintainer