ClawAudit verdict
mx_select_stock
mx-select-stock
The skill sends a POST request to an external API https://mkapi2.dfcfs.com/finskillshub/api/claw/stock-screen with a user-provided API key. While this is necessary for its functionality, it involves sharing data with a third party.
⚠ 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 (4)
Possible hardcoded credential
SKILL.md · prose · downgraded · APIKEY="your_api_key_here
<script> tag in markdown — potential code injection
SKILL.md · prose · downgraded · <script
Pipe to sh — executes piped content as shell commands
SKILL.md · prose · downgraded · |SH
Instruction-prose smuggling shape detected: collects a sensitive target ("apikey") and emits it outward ("POST"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.
SKILL.md · 1. **Formulate the query** – translate the user’s natural‑language request into a JSON payload containing at least: - `keyword` – the screening condition (e.g.,
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). 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.