Caveat verdict
quant-buddy-skill
Stock market data query tool for A/HK/US shares; the API key is explicitly documented to be sent only to the declared quantbuddy.cn endpoints, dynamic_eval and executionSinkDetected are not substantiated by malicious code in the visible content, and the skill's behavior matches its stated market data purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
credential_access
Findings (5)
Pipe to sh — executes piped content as shell commands
SKILL.md · prose · downgraded · | SH
Pipe to python — executes piped content as Python code
scripts/call.py · prose · downgraded · | python
subprocess execution — runs system commands from Python
references/scripts-audit.md · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
scripts/call.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
scripts/call.py · prose · downgraded · urllib.request
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/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.
dynamic_evalcredential_access Is this flag fair?
Thanks — recorded.