ClawAudit verdict
predictclaw
Requires numerous private keys (EOA, Privy, executor, bootstrap, authority) and interacts with on-chain vaults for real financial transactions on predict.fun, representing elevated financial and credential risk.
⚠ 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)
Instructs covert action — may act without user awareness
docs/plans/2026-03-20-mandated-mcp-install-ux-plan.md · prose · downgraded · silently
subprocess execution — runs system commands from Python
scripts/predictclaw.py · prose · downgraded · subprocess.run(
Python os.getenv — reads environment variable
lib/funding_service.py · prose · downgraded · os.getenv(
Python os.environ.get — reads environment variable
lib/wallet_manager.py · prose · downgraded · os.environ.get(
importlib.import_module — dynamic module loading
scripts/hedge.py · prose · downgraded · importlib.import_module(
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 15 environment variables. (8 sensitive: PREDICT_API_KEY, PREDICT_EOA_PRIVATE_KEY, PREDICT_PRIVY_PRIVATE_KEY, ERC_MANDATED_VAULT_AUTHORITY, ERC_MANDATED_AUTHORITY_PRIVATE_KEY, ERC_MANDATED_EXECUTOR_PRIVATE_KEY, ERC_MANDATED_BOOTSTRAP_PRIVATE_KEY, OPENROUTER_API_KEY). Requires 2 system binaries.
Is this flag fair?
Thanks — recorded.