Caveat verdict
token-optimizer
openclaw-token-optimizer
Token cost-control toolkit for lazy context loading, model routing, and token budgeting; security notes explicitly confirm no network access, no code execution, and local-only data.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (9)
Possible hardcoded credential
references/PROVIDERS.md · code · API_KEY="sk-ant-...
Uses eval() — can execute arbitrary code
SECURITY.md · code · eval(
References sudo — requests elevated privileges
SECURITY.md · code · sudo
Uses exec() — may execute shell commands
SECURITY.md · code · exec(
Accesses OpenClaw config/secrets directly
references/PROVIDERS.md · prose · downgraded · ~/.openclaw/openclaw.json
Sets world-executable permissions
SECURITY.md · code · chmod 777
References agent memory files
CHANGELOG.md · prose · downgraded · MEMORY.md
Python os.environ.get — reads environment variable
scripts/model_router.py · prose · downgraded · os.environ.get(
Popular HTTP library — network access
scripts/model_router.py · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.