plan-payroll
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Data Ingestion Considerations: The skill is designed to process financial data from various connectors (QuickBooks, PayPal, Stripe, Square) and user-provided CSV files. Ingesting data from external sources is a common pattern that warrants review, as such data can occasionally contain unexpected content designed to influence the agent.\n
- Ingestion points: Data is pulled from financial APIs and CSV uploads as defined in
SKILL.md.\n - Boundary markers: The instructions do not define specific delimiters to separate external data from system prompts.\n
- Capability inventory: The skill utilizes
Bash,WebFetch, andReadtools as listed inSKILL.md.\n - Sanitization: The instructions do not explicitly detail sanitization or validation routines for the ingested data.\n- Human-in-the-Loop Safeguards: A strong security feature of this skill is the inclusion of mandatory approval gates. The instructions explicitly state that the owner must approve all handoffs, confirmations, and reminders before any action is taken. This requirement significantly reduces the risk associated with automated data processing.
Audit Metadata