ClawAudit verdict
team-resurrection
Agent team migration tool requiring user confirmation for all sensitive operations and explicitly warning about sensitive files in migration packages.
⚠ 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.
Permission integrity
agent_memory
Findings (6)
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf ~
References agent memory files
SKILL.md · frontmatter · MEMORY.md
subprocess execution — runs system commands from Python
clone.py · prose · downgraded · subprocess.run(
subprocess with shell=True — command injection vector
clone.py · prose · downgraded · subprocess.run(cmd, shell=True
HTTP request to bare IP address — common in malicious payloads
migrate.py · prose · downgraded · http://127.0.0.1
Python shutil file operation — copies/moves/deletes files
clone.py · prose · downgraded · shutil.copytree(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary.
agent_memoryprocess_exec Is this flag fair?
Thanks — recorded.