ClawAudit verdict
soul-guardian
clawsec-openclaw-soul-guardian
Accesses credentials AND makes external network calls
Drift detection and auto-restore for agent workspace files; network behavior is explicitly 'none by default' and all operations (baseline comparison, quarantine, restore) are local-only security tooling.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Accesses credentials AND encodes data — may obfuscate stolen credentials
LLM02 · ASI03 · ASI04
Permission integrity
network_out
credential_access
Findings (5)
subprocess execution — runs system commands from Python
scripts/install_launchd_plist.py · prose · downgraded · subprocess.run(
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
Python shutil file operation — copies/moves/deletes files
scripts/onboard_state_dir.py · prose · downgraded · shutil.rmtree(
Popular HTTP library — network access
scripts/soul_guardian.py · prose · downgraded · got
Python os.environ.get — reads environment variable
scripts/test_install_launchd_plist.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outcredential_accessdata_encoding Thanks — recorded.