ClawAudit verdict
sky-dome-taiyi
A persona-grade AI agent workflow system providing reasoning frameworks and memory protocols; it contains only instructional content with no scripts, credentials, or external network calls.
⚠ 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 (5)
Pipe to python — executes piped content as Python code
SKILL.md · code · | python
Possible prompt injection — attempts to redefine agent identity
SKILL.md · code · You are now
subprocess execution — runs system commands from Python
scripts/taiyi_bench.py · prose · downgraded · subprocess.run(
Python urllib.request — network access
scripts/taiyi_api_smoke.py · prose · downgraded · urllib.request
Python shutil file operation — copies/moves/deletes files
scripts/taiyi_stage.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.