lovstudio-expense-report
Warn
Audited by Snyk on Jul 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In SKILL.md Step 1–2 the agent ingests outsider-provided free text directly from the user (“Text descriptions: Parse the user's text…”) to extract fields (vendor/item/note/amount/date) and then classifies them before asking for confirmation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata