procountor-fi
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted external data from Procountor which may contain malicious instructions targeting the agent.
- Ingestion points: Data is retrieved through methods like
apideck.accounting.invoices.listandapideck.accounting.bills.listinSKILL.md. - Boundary markers: The provided TypeScript examples do not demonstrate the use of delimiters or specific instructions to the model to ignore embedded data instructions.
- Capability inventory: The skill allows the agent to read, write, and reconcile sensitive accounting entities including invoices, payments, and journal entries.
- Sanitization: No explicit data sanitization or validation logic is presented in the integration examples to mitigate potential injection within field values.
Audit Metadata