ClawAudit verdict
cost-optimizer
open-optimise
API cost optimization skill with local configuration and routing scripts; no capabilities and content describes legitimate cost-reduction workflows with user approval gating.
⚠ 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 (6)
Recursive delete from root or home — destructive command
GUIDE.md · code · rm -rf ~
Pipe to bash — executes piped content as shell commands
README.md · prose · downgraded · | bash
Dynamic Function constructor — equivalent to eval()
scripts/compaction-log.sh · prose · downgraded · new Function(
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
Uses exec() — may execute shell commands
scripts/dedup-detector.sh · prose · downgraded · exec(
Node http/https module — low-level network access
scripts/fallback-validator.sh · prose · downgraded · require('https')
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B/D/F). 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.