next-ops-scan

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection.
  • Ingestion points: Data is ingested from the Next Commerce Admin API in scripts/next_ops_scan.py.
  • Boundary markers: The generated next_ops_scan_summary.md file does not utilize delimiters or specific instructions to isolate order data from the agent's instructions.
  • Capability inventory: The skill uses the Bash tool to execute its bundled Python script and writes output files to the local disk.
  • Sanitization: External data fields, such as order numbers and status reasons, are interpolated directly into the summary report without escaping or sanitization, which could allow maliciously crafted order data to influence the agent when the summary is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 05:32 PM
Security Audit — agent-trust-hub — next-ops-scan