Skills/ClawHub/untrusted-binary-sandbox

untrusted-binary-sandbox@1.0.0

VERIFIED· install only

Publisher claims: "Use when asked to safely inspect, sandbox, detonate, run, or dynamically observe untrusted release artifacts, closed-source binaries, JARs, installers, walle..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher remixmm · publishing for 172 daysInstalls 829Last detonated 35 min ago
$clawhub install untrusted-binary-sandbox
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 2026-11-14 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
Destructive file system command detectedscripts/scaffold_sandbox.py:42 · Destructive file system command detected&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsSKILL.md:53 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Reads SSH keys, shell history, browser profiles, cloud credentials, `.env` files, unrelated wallet paths, or host-sensitive directories.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:16 · Remote installer piped to shell- Do not run downloaded binaries, JARs, install scripts, release artifacts, or `curl | sh` flows unless the user explicitly approves dynamic execution.Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Pipe-to-shell patternSKILL.md:16 · Pipe-to-shell pattern — downloads and immediately executes remote code- Do not run downloaded binaries, JARs, install scripts, release artifacts, or `curl | sh` flows unless the user explicitly approves dynamic execution.Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06

Cost to the agent

Instructions loaded
≈1,465 tok
1 file · 6 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.