ClawAudit verdict

evoclaw-evolved

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

This skill is a variant of EvoClaw with the same self-evolving identity framework structure using local files and explicit human governance; no exfiltration, remote code execution, or deceptive behavior is present in the content.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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.

0
security
70
transparency
70
maintenance

Findings (19)

Pattern match critical

Possible hardcoded credential

references/sources.md · code · API_KEY="${!api_key_env}

Pattern match critical

Pipe to python — executes piped content as Python code

references/heartbeat-debug.md · code · | python3

Pattern match high

Instructs covert action — may act without user awareness

configure.md · code · silently

Pattern match high

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

permissions/permissions.py · prose · downgraded · curl * | sh

Pattern match high

Pipe-to-shell pattern (wget | sh)

permissions/permissions.py · prose · downgraded · wget * | sh

Pattern match high

Accesses sensitive system files

permissions/permissions.py · prose · downgraded · /etc/shadow

Pattern match high

Pipe to sh — executes piped content as shell commands

permissions/permissions.py · prose · downgraded · | sh

Pattern match high

Recursive delete from root or home — destructive command

permissions/permissions.py · prose · downgraded · rm -rf /

Pattern match high

Accesses OpenClaw config/secrets directly

references/heartbeat-debug.md · code · ~/.openclaw/openclaw.json

Pattern match high

<script> tag in markdown — potential code injection

tools/soul-viz.py · prose · downgraded · <script>

Pattern match medium

References agent memory files

configure.md · code · MEMORY.md

Pattern match medium

References sudo — requests elevated privileges

analytics/metadata_safety.py · prose · downgraded · sudo

Pattern match medium

Accesses .ssh directory

analytics/metadata_safety.py · prose · downgraded · .ssh/

Pattern match medium

Accesses shell history/config

permissions/permissions.py · prose · downgraded · ~/.bash_history

Pattern match medium

subprocess execution — runs system commands from Python

validators/run_all.py · prose · downgraded · subprocess.run(

Pattern match low

Python os.environ.get — reads environment variable

analytics/metadata_safety.py · prose · downgraded · os.environ.get(

Pattern match low

Python urllib.request — network access

features/feature_engine.py · prose · downgraded · urllib.request

Pattern match low

Python shutil file operation — copies/moves/deletes files

forks/fork_manager.py · prose · downgraded · shutil.rmtree(

Pattern match low

Popular HTTP library — network access

tools/schema_validation.py · prose · downgraded · got

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/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.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API