pluggy-open-finance
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents architectural patterns for ingesting and displaying third-party financial data, which inherently introduces a surface for indirect instructions or malicious content within transaction descriptions or merchant metadata.
- Ingestion points: Webhook payloads and API responses for accounts, transactions, and investments as described in
rules/sync-strategies.mdandrules/transaction-enrichment.md. - Boundary markers: The provided code snippets do not demonstrate the use of delimiters or instructions to ignore content within financial data fields.
- Capability inventory: The examples suggest fetching dynamic URLs provided in webhooks and rendering external image URLs for merchant logos in UI components.
- Sanitization: While the SDK handles typical API interactions, the documentation does not explicitly show sanitization steps for displaying raw merchant descriptions or logo URLs.
Audit Metadata