ClawAudit verdict
soulsync
soul-sync
Skill personalizes agent workspace files through user conversation; the safety section explicitly states all processing is local with no data transmitted externally and all OAuth flows are opt-in with explicit user consent.
⚠ 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 (9)
Possible hardcoded credential
lib/importers/github.py · prose · downgraded · password="):
token = line.split(
References agent memory files
SKILL.md · frontmatter · MEMORY.md
subprocess execution — runs system commands from Python
lib/importers/github.py · prose · downgraded · subprocess.run(
Accesses shell history/config
lib/importers/local_system.py · prose · downgraded · ~/.bash_history
Accesses .ssh directory
lib/importers/local_system.py · prose · downgraded · .ssh/
Popular HTTP library — network access
SKILL.md · prose · downgraded · Got
Python os.environ.get — reads environment variable
lib/conversation.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
lib/importers/github.py · prose · downgraded · urllib.request
Python shutil file operation — copies/moves/deletes files
tests/test_full_e2e.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.