ClawAudit verdict
predictclaw
predictclaw-publish-docs-20260320
The skill's content appears to be documentation and installation instructions, with no evidence of malicious 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 (5)
Possible hardcoded credential
tests/test_auth.py · prose · downgraded · token="jwt-token
Instructs covert action — may act without user awareness
README.md · prose · downgraded · silently
subprocess execution — runs system commands from Python
scripts/predictclaw.py · prose · downgraded · subprocess.run(
importlib.import_module — dynamic module loading
scripts/hedge.py · prose · downgraded · importlib.import_module(
Python os.getenv — reads environment variable
scripts/predictclaw.py · prose · downgraded · os.getenv(
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
Requires 2 environment variables. Requires 1 system binary.
Is this flag fair?
Thanks — recorded.