lifestyle-creep
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill performs analytical tasks on financial summaries provided by the platform and lacks access to sensitive system resources or external network connections.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data via the
spending_summarytool. While this provides an attack surface for indirect instructions embedded in transaction descriptions, the skill lacks the necessary capabilities (such as network operations, file writing, or command execution) to exfiltrate data or cause system harm. - Ingestion points: Reads spending category data via the
spending_summarytool (SKILL.md). - Boundary markers: None explicitly defined for the tool output.
- Capability inventory: No subprocess calls, network operations, or file-write capabilities were detected.
- Sanitization: None mentioned for processing transaction category names.
Audit Metadata