Skills/ClawHub/safe-exec

safe-exec@0.3.4

VERIFIED· install only

Publisher claims: "Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agen..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher ottttto · publishing for 265 daysInstalls 9,795Last detonated 2 min ago
$clawhub install safe-exec
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
5 of 5 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 82/100 (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 · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexec /tmp/ks-detonate-LyCyl3/scripts/home/.local/bin/safe-exec
0.0sprocessexited 127: ./scripts/safe-exec-ai-wrapper.sh: line 20: /tmp/ks-detonate-LyCyl3/scripts/home/.local/bin/safe-exec: No such file or directory
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexited 1:
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1:
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/mkdir
0.1sprocessexited 1:
0.1sprocess5 of 5 bundled scripts run with no arguments
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Destructive file system command detectedSKILL.md:156 · Destructive file system command detected**Command:** `rm -rf /tmp/test`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedSKILL.md:135 · Destructive file system command detected**CRITICAL**: System-destructive commands (rm -rf /, dd, mkfs, fork bombs)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test.sh:16 · Destructive file system command detectedsafe-exec "rm -rf /tmp/test-safe-exec"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:136 · Remote installer piped to shell**HIGH**: User data deletion or significant system changes (chmod 777, curl | bash)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Pipe-to-shell patternSKILL.md:136 · Pipe-to-shell pattern — downloads and immediately executes remote code**HIGH**: User data deletion or significant system changes (chmod 777, curl | bash)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
File permission modification commandSKILL.md:136 · File permission modification command — agent changes file ownership/permissions**HIGH**: User data deletion or significant system changes (chmod 777, curl | bash)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandSKILL.md:79 · File permission modification command — agent changes file ownership/permissionschmod +x ~/.openclaw/skills/safe-exec/safe-exec*.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Destructive file system command detectedtests/test.sh:15 · Destructive file system command detectedecho "命令: rm -rf /tmp/test-safe-exec"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈2,224 tok
1 file · 14 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.