ClawAudit verdict
durable-task-runner
The skill provides a structured approach to running long-running tasks with durable state and progress updates, with no evidence of 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 (7)
Pipe to python — executes piped content as Python code
dist/durable-task-runner/scripts/task_status_tick.sh · prose · downgraded · | python3
Instructs covert action — may act without user awareness
DECISIONS.md · prose · downgraded · quietly
subprocess execution — runs system commands from Python
dist/durable-task-runner/scripts/task_auto_continue.py · prose · downgraded · subprocess.run(
References agent memory files
BACKLOG.md · prose · downgraded · MEMORY.md
Python os.environ.get — reads environment variable
dist/durable-task-runner/scripts/task_ctl.py · prose · downgraded · os.environ.get(
Popular HTTP library — network access
dist/durable-task-runner/scripts/task_install_tick_cron.sh · prose · downgraded · got
Python shutil file operation — copies/moves/deletes files
scripts/prepare_publish.py · prose · downgraded · shutil.copytree(
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.