Skills/ClawHub/soul-guardian

soul-guardian@0.0.6

VERIFIED· install only

Publisher claims: "Drift detection + baseline integrity guard for agent workspace files with automatic alerting support" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher davida-ps · publishing for 192 daysInstalls 4,755Last detonated 29 min ago
$clawhub install soul-guardian
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
3 of 3 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 2026-11-22 and scored it 83/100 (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
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: soul_guardian.py not found at /tmp/ks-detonate-qOGGAv/scripts/home/work/acme-api/.claude/skills/soul-guardian/skills/soul-guardian/scripts/soul_guardian.py; pass --workspace-root correctly
0.1sprocessbundled script run in the sandbox with no arguments
0.2sfilesystemwrote ~/.openclaw/soul-guardian/soul-guardian/policy.json
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: soul_guardian.py: error: the following arguments are required: cmd
0.3sprocess3 of 3 bundled scripts run with no arguments
0.3sprocessscript backend runs setup only
0.3sprocessscript backend runs setup only
0.3sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/install_launchd_plist.py:244 · Python subprocess execution detectedsubprocess.run(["/bin/launchctl", "enable", f"gui/{uid}/{label}"], check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/test_soul_guardian.py:24 · Python subprocess execution detectedreturn subprocess.run(cmd, cwd=str(cwd), text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingscripts/test_install_launchd_plist.py:65 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/onboard_state_dir.py:139 · File permission modification command — agent changes file ownership/permissionsprint("- The external state dir can contain approved snapshots, patches, and quarantined copies of drifted prompt/instruction files; keep permissions restrictive (e.g., chmod 700; go-rwx).")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Dynamic module loadingscripts/test_install_launchd_plist.py:66 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/install_launchd_plist.py:59 · Python subprocess execution detectedreturn subprocess.run(["/bin/launchctl", *args], check=False, text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/install_launchd_plist.py:237 · Python subprocess execution detectedres = subprocess.run(["/bin/launchctl", "bootstrap", f"gui/{uid}", str(plist_path)], text=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/install_launchd_plist.py:245 · Python subprocess execution detectedsubprocess.run(["/bin/launchctl", "kickstart", "-k", f"gui/{uid}/{label}"], check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/test_install_launchd_plist.py:22 · Python subprocess execution detectedreturn subprocess.run(cmd, text=True, capture_output=True, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈1,880 tok
1 file · 10 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.

soul-guardian@0.0.6 safety verdict: Verified (install only) — KillerSkills