ClawAudit verdict
cost-watchdog
llm-cost-watchdog
LLM cost tracking and budget enforcement tool that reads local session JSONL logs and queries provider pricing APIs; all executionSink references are documented CLI commands matching the stated cost monitoring 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.
Findings (5)
Raw model control tokens — prompt injection via token manipulation
references/calculators.md · code · <|im_start|>
subprocess execution — runs system commands from Python
tests/test_cost_watchdog.py · prose · downgraded · subprocess.run(
Python urllib.request — network access
scripts/_sources.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
scripts/_sources.py · prose · downgraded · os.environ.get(
Python shutil file operation — copies/moves/deletes files
tests/test_cost_watchdog.py · prose · downgraded · shutil.rmtree(
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
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.