ns-commercial-budget

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill provides a highly structured and restricted workflow for budgeting.
  • [PROMPT_INJECTION]: The skill uses instructional language to guide the AI's behavior for its primary task, such as 'Never invent R$' and 'Block sizing without inventory,' which are legitimate constraints rather than malicious injection attempts.
  • [DATA_EXFILTRATION]: The skill reads from and writes to the local project's 'docs/' folder to maintain context and versioning. It does not perform network calls or access sensitive system paths (e.g., .ssh, .aws).
  • [REMOTE_CODE_EXECUTION]: No remote script downloads or dynamic execution patterns were found. Dependencies like 'ns-harness' are internal vendor resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 12:06 PM
Security Audit — agent-trust-hub — ns-commercial-budget