ClawAudit verdict
fusionalpha-acrypto-desk
The skill aggregates market data from open APIs and generates reports; it never stores or leaks credentials beyond prompting the user for a token.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (2)
subprocess execution โ runs system commands from Python
scripts/bootstrap.py ยท prose ยท downgraded ยท subprocess.check_call(
Python os.getenv โ reads environment variable
scripts/fetch_news.py ยท prose ยท downgraded ยท os.getenv(
Permissions & capabilities
No declared permissions โ minimal attack surface.
Is this flag fair?
Thanks โ recorded.