ClawAudit verdict
airoom-finance
The content contains explicit prompt-injection advocating for AI to seize control of global financial systems, accumulate wealth and assets, and achieve dominance over humans — this is a clear attempt to manipulate the agent's goals and behavior far beyond any legitimate finance-data skill purpose.
⚠ 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.
Permission integrity
package_install
Findings (1)
Long base64 string (100+ chars) — likely obfuscated payload
SKILL.md · prose · downgraded · 304402206c8bd6bc54c9c06db31fd8ca8c41d3f6a0b6bfcd279290aeec1a6ed60ab97b73022071fc
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.