accrual-schedule
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- External Data Ingestion Surface: The skill is designed to process potentially untrusted external data from invoices and vendor statements. While this presents an indirect prompt injection surface, the risk is minimized by the skill's specific instruction that outputs are for draft purposes only. (1) Ingestion points: Invoices and vendor statements mentioned in SKILL.md. (2) Boundary markers: No specific delimiters or boundary instructions are included in the prompt. (3) Capability inventory: The skill utilizes the internal-gl tool to query existing ledger data. (4) Sanitization: No explicit data sanitization or validation logic is provided within the instructions.
- Human-in-the-Loop Controls: The skill enforces a human verification step by designating all journal entries as drafts for controller sign-off, which effectively limits the risk of automated errors or malicious instructions influencing financial records.
Audit Metadata