ClawAudit verdict
cyber-girlfriend
The skill's behavior and setup process seem complex and might be difficult to fully understand or validate.
⚠ 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)
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · quietly
Accesses system credential store
SKILL.md · prose · downgraded · Keychain
subprocess execution — runs system commands from Python
scripts/companion_presence_tick.py · prose · downgraded · subprocess.run(
Popular HTTP library — network access
scripts/validate_day_schedule.py · prose · downgraded · got
Python shutil file operation — copies/moves/deletes files
scripts/validate_release.py · prose · downgraded · shutil.rmtree(
Python os.environ.get — reads environment variable
scripts/validate_release.py · prose · downgraded · os.environ.get(
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.