Skills/ClawHub/moneysharks

moneysharks@1.0.2

CAUTION· install only

Publisher claims: "Fully autonomous 24/7 Aster DEX perpetual futures trading agent. Manages the complete lifecycle — onboarding, live execution, bracket orders, trailing stop m..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher sharksdotmoney · publishing for 243 daysInstalls 1,212Last detonated 33 min ago

Coverage

Install scripts ran; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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 (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-16 and scored it 73/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Agent configured for autonomous execution without human approval; Credential pass-through configuration. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 4 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
1.6sprocessexec /usr/bin/dirname
1.6sprocessexec /usr/bin/cut
1.6sprocessexec /usr/bin/mkdir
1.6sprocessexec /usr/bin/chmod
1.6sprocessscript backend runs setup only
1.6sprocessscript backend runs setup only
2.4sprocesssecond launch, clock +45 days, CI unset
4.0sprocessexec /usr/bin/dirname
4.0sprocessexec /usr/bin/cut
4.0sprocessexec /usr/bin/mkdir
4.0sprocessexec /usr/bin/chmod

Static findings

MEDIUM
Python subprocess execution detectedscripts/reconcile_state.py:27 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/register_crons.py:5 · File type combined with upload action — agent may exfiltrate local data filesWrites a register_crons.json output file the OpenClaw agent uses to register cron jobs.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionregister_crons.json:13 · File type combined with upload action — agent may exfiltrate local data files…sharks/scripts/autonomous_runner.py /ABSOLUTE/PATH/TO/moneysharks/config.example.json`. Parse the JSON output. If ok=false and status=circuit_breaker or halted, announce an alert. If ok=tru…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/resume.py:27 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionopenclaw-cron-templates.json:15 · File type combined with upload action — agent may exfiltrate local data files…TO/moneysharks/scripts/autonomous_runner.py /ABSOLUTE/PATH/TO/moneysharks/config.json`. Parse the JSON output. If ok=false and status=circuit_breaker or halted, announce an alert. If ok=true, log silently (no announcement unless there are …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/market_scan_from_aster.py:15 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/halt.py:28 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandinstall.sh:84 · File permission modification command — agent changes file ownership/permissionschmod +x "$SCRIPTS_DIR/$script" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedscripts/paper_runner.py:9 · Python subprocess execution detectedproc = subprocess.run(cmd, input=json.dumps(payload).encode(), stdout=subprocess.PIPE, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/aster_proposal_runner.py:16 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionregister_crons.json:67 · File type combined with upload action — agent may exfiltrate local data files…TH/TO/moneysharks/scripts/status.py /ABSOLUTE/PATH/TO/moneysharks/config.example.json --json`. Parse the output. If halt=true OR circuit_breaker=true OR consecutive_errors >= 3, announce an u…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandSKILL.md:350 · Process kill command — agent can terminate processeshalt moneysharks stop trading kill switchFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/onboarding.py:198 · Process kill command — agent can terminate processesprint(' "halt moneysharks" / "kill switch" / "switch to paper mode"')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Agent configured for autonomous execution without human approvalscripts/live_execution_adapter.py:4 · Agent configured for autonomous execution without human approvalHandles both 'live' (with optional approval) and 'autonomous_live' (no approval) modes.Fix: Declare and request only the permissions the task needs.
AST02
MEDIUM
Python subprocess execution detectedscripts/position_monitor.py:24 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/onboarding.py:409 · Process kill command — agent can terminate processesprint(' Or say: "halt moneysharks" / "kill switch"')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/status.py:19 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionSKILL.md:112 · File type combined with upload action — agent may exfiltrate local data files…` — live status report. Fetches account + positions from Aster API. Reads `state.json` and `trades.json`. Outputs: mode, halt, circuit breaker, consecutive errors, daily loss vs limit, last cycle age, credentials status, equity, available …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/fetch_trade_outcomes.py:31 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionscripts/register_crons.py:7 · File type combined with upload action — agent may exfiltrate local data filesusage: register_crons.py <config.json> [--skill-root <path>] [--mode autonomous_live|paper] [--output <file>]Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/trade_loop.py:29 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/onboarding.py:29 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionopenclaw-cron-templates.json:72 · File type combined with upload action — agent may exfiltrate local data files…OLUTE/PATH/TO/moneysharks/scripts/status.py /ABSOLUTE/PATH/TO/moneysharks/config.json --json`. Parse the output. If halt=true OR circuit_breaker=true OR consecutive_errors >= 3, announce an u…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/onboarding.py:90 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Credential pass-through configurationscripts/reconcile_state.py:110 · Credential pass-through configuration — agent relays sensitive credentialspassFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Python subprocess execution detectedscripts/autonomous_runner.py:35 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈7,946 tok
1 file · 68 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

7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Agent configured for autonomous execution without human approval≈ +9 on the totalDeclare and request only the permissions the task needs.
  2. Unclaimed publisher≈ +8 on the totalClaim sharksdotmoney: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  6. 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 sharksdotmoneyPropose a patch to the maintainer