Skills/ClawHub/agent-easy-http

agent-easy-http@1.1.0

VERIFIED· install only

Publisher claims: "Deploy an HTTP(S) proxy that exposes OpenClaw agent capability as a REST API over your network IP (e.g. http://<your-server-ip>:7720). Use when asked to "start agent-easy-http", "expose openclaw agent as HTTP", "deploy openclaw agent HTTP service", "create internal HTTP API for agent", or "start the agent gateway". HTTP by default (zero-friction); optional HTTPS with self-signed SAN certificates for production / cross-host scenarios. Includes mandatory API Key auth, deny-list filter, prompt-injection hardening, and direct integration with OpenClaw native /hooks/agent (millisecond dispatch + automatic hook:<uuid> session isolation per request). Thin proxy layer; use skill-to-http-flash for per-skill API endpoints." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher songhonglei · publishing for 1 daysInstalls 657Last detonated 23 h ago
$clawhub install agent-easy-http
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Privileged sudo commandSKILL.md:357 · Privileged sudo command — agent may execute with elevated privilegessudo cp <workspace>/.http/certs/server.crt /usr/local/share/ca-certificates/Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/gen_cert.py:117 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandSKILL.md:358 · Privileged sudo command — agent may execute with elevated privilegessudo update-ca-certificatesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/gen_cert.py:53 · Python subprocess execution detectedresult = 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/gen_cert.py:160 · Python subprocess execution detectedout = subprocess.check_output(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/gen_cert.py:134 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/watchdog.sh:224 · Process kill command — agent can terminate processeskill -TERM "$pid" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/server.py:890 · Python subprocess execution detectedsubprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/watchdog.sh:78 · Process kill command — agent can terminate processeskill -0 "$pid" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/server.py:641 · Python subprocess execution detectedr = 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/gen_cert.py:215 · Python subprocess execution detectedsubprocess.run(["openssl", "version"], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
URL to a private-network addressSKILL.md:156 · URL to a private-network address — a LAN or development targethttps://192.168.1.10:7720/skills/hello-env/runFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedscripts/init_wizard.py:125 · Python subprocess execution detectedresult = 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/server.py:975 · Python subprocess execution detectedsubprocess.run(["bash", str(watchdog_sh), "stop"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/watchdog.sh:134 · Process kill command — agent can terminate processesif kill -0 "$new_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
URL to a private-network addressSKILL.md:162 · URL to a private-network address — a LAN or development targethttps://192.168.1.10:7720/agent/runFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Process kill commandscripts/watchdog.sh:227 · Process kill command — agent can terminate processeskill -9 "$pid" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/watchdog.sh:70 · Process kill command — agent can terminate processeskill -0 "$pid" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/init_wizard.py:529 · Python subprocess execution detectedsubprocess.run([sys.executable, str(script)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈2,972 tok
1 file · 12 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.