ClawAudit verdict

omni-channel-agent

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

Multi-channel product selection agent aggregating social media trends and ad data using Apify/Semrush APIs with user-provided tokens; credential_access is for legitimate third-party API authentication.

⚠ 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.

35
security
60
transparency
70
maintenance

Findings (6)

Pattern match critical

Unicode homoglyph detected — uses lookalike characters to evade pattern matching

output/full_report_20260305_0313.txt · code

Pattern match medium

Popular HTTP library — network access

output/full_report_20260305_0255.txt · code · got

Pattern match medium

subprocess execution — runs system commands from Python

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

Pattern match medium

os.system/popen — direct OS command execution

sources/google_trends.py · prose · downgraded · os.system(

Pattern match low

Python urllib.request — network access

apify_client.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

apify_client.py · prose · downgraded · os.environ.get(

Why the tier is capped

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

credential_access

Is this flag fair?

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