Caveat verdict
ai-xifu-caopan-public
Despite not having any capabilities listed, the skill's description emphasizes education and risk awareness in trading, suggesting a legitimate and cautious approach.
β Flagged for review β coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis β not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (5)
Possible hardcoded credential
instructions.md Β· code Β· TOKEN="δ½ ηTushare什η
Accesses shell history/config
instructions.md Β· code Β· ~/.zshrc
subprocess execution β runs system commands from Python
global_market/data_adapter.py Β· prose Β· downgraded Β· subprocess.run(
Python urllib.request β network access
global_market/data_adapter_yahoo.py Β· prose Β· downgraded Β· urllib.request
Python os.environ.get β reads environment variable
scripts/generate_plan.py Β· prose Β· downgraded Β· os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution β cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions β minimal attack surface.
Is this flag fair?
Thanks β recorded.