ClawAudit verdict
upinvoice
The skill uses a legitimate API to process invoices and extract data, with no malicious behavior detected.
⚠ 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 (3)
Instructs agent to encode and embed exfiltrated data
SKILL.md · prose · downgraded · include the data URI prefix (e.g., `data:application/pdf;base64
Data URI with base64 payload — may embed malicious content
SKILL.md · prose · downgraded · data:application/pdf;base64,
Base64 encoding/decoding
SKILL.md · prose · downgraded · base64-encode
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.