skills/mphinance/alpha-skills/invoice/Gen Agent Trust Hub

invoice

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied project briefs to populate invoice fields (line items, descriptions, addresses) in the generated HTML artifact. While this is the primary function, the instructions lack explicit sanitization or boundary markers to prevent the agent from executing instructions embedded within the user data.
  • Ingestion points: User-provided brief or prompt (SKILL.md)
  • Boundary markers: Absent in the workflow description
  • Capability inventory: HTML artifact generation (SKILL.md)
  • Sanitization: No explicit sanitization or escaping instructions provided for the interpolated data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 07:50 AM