sales-tax-nexus

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests transaction descriptions and notes from external sources which constitute untrusted data.
  • Ingestion points: The skill uses transaction_search and spending_summary to process external transaction data as specified in SKILL.md.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands embedded within transaction notes.
  • Capability inventory: The skill uses the export_transactions tool which provides data-writing capabilities.
  • Sanitization: No evidence of filtering or sanitization of ingested transaction fields is provided in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:56 AM