rillet
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve and process external accounting data from Rillet, such as invoices, bills, and ledger accounts. This external content could contain malicious instructions meant to manipulate the agent's behavior in downstream tasks.
- Ingestion points: External data is ingested through the Apideck Accounting unified API methods (e.g.,
apideck.accounting.invoices.list,apideck.accounting.bills.get) as described inSKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to the agent to disregard instructions that might be embedded within the retrieved Rillet data.
- Capability inventory: The skill allows the agent to read and write accounting data, which can then be used in subsequent logic or tool invocations.
- Sanitization: No explicit sanitization, filtering, or validation of the retrieved accounting data is documented within the skill's instructions.
Audit Metadata