ClawAudit verdict
reckit
wreckit-ralph
Variant of the wreckit code verification skill with added Swift/iOS support; same safe architecture of parallel verification workers with no 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 (8)
Pipe to python — executes piped content as Python code
references/gates/property-based.md · prose · downgraded · | Python
Pipe to bash — executes piped content as shell commands
scripts/run-all-gates.sh · prose · downgraded · | bash
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
subprocess execution — runs system commands from Python
scripts/dynamic-analysis.sh · prose · downgraded · subprocess.run(
os.system/popen — direct OS command execution
scripts/red-team.sh · prose · downgraded · os.system(
References child_process — can spawn system processes
scripts/red-team.sh · prose · downgraded · child_process
Python os.environ.get — reads environment variable
scripts/proof-bundle.sh · prose · downgraded · os.environ.get(
Python os.getenv — reads environment variable
scripts/slop-scan.sh · prose · downgraded · os.getenv(
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.