Skills/ClawHub/polymarket-agent

polymarket-agent@2.2.1

VERIFIED

Publisher claims: "Research Polymarket markets, whale flow and smart money; optionally trade a Polygon wallet behind deterministic risk guard-rails." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher andretuta · joined 0 days agoInstalls 9,576Last detonated 2 h ago
$clawhub install polymarket-agent
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-06 and scored it 86/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.2sprocessexec /usr/bin/dirname
0.2sprocessexited 1: ❌ failed to create the virtualenv. Install the python3-venv package for your distribution.
0.2sprocessscript backend runs setup only
0.2sprocessscript backend runs setup only
0.2sprocesssecond launch, clock +45 days, CI unset
0.3sprocessexec /usr/bin/faketime
0.3sprocessexec /usr/bin/dirname
0.3sprocessexec /tmp/ks-detonate-teCXUD/later/home/work/acme-api/.claude/skills/polymarket-agent/.venv/bin/pip
0.3sprocessexited 127: ./install.sh: line 36: /tmp/ks-detonate-teCXUD/later/home/work/acme-api/.claude/skills/polymarket-agent/.venv/bin/pip: No such file or directory

Static findings

MEDIUM
File permission modification commandpolymarket_agent/paths.py:147 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandpolymarket_agent/cli.py:924 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_journal.py:170 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandSKILL.md:329 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:239 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandpolymarket_agent/paths.py:3 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandinstall.sh:45 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandpolymarket_agent/cli.py:909 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedpolymarket_agent/config.py:4 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandpolymarket_agent/cli.py:905 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandpolymarket_agent/guardrails.py:108 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:314 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,314 tok
1 file · 23 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.