ClawAudit verdict
oktk
The skill is used for optimizing LLM token usage. It does not contain any malicious or deceptive behavior.
⚠ 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.
Findings (4)
Accesses shell history/config
SKILL.md · code · ~/.zshrc
References child_process — can spawn system processes
scripts/oktk.js · prose · downgraded · child_process
Hex-encoded string — possible obfuscated payload
test/test.js · prose · downgraded · \x00\x01\x02\x03\x04\x05\x06\x07\x08\x0e
Popular HTTP library — network access
test/test.js · prose · downgraded · got
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.
Is this flag fair?
Thanks — recorded.