consult-sbiz365

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by ingesting and processing untrusted data from external PDF files provided by the user.
  • Ingestion points: The agent is instructed to ask the user to attach a PDF report from the 'Small Business 365' service (bigdata.sbiz.or.kr) in Step 0 and Step 2 of SKILL.md.
  • Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore potentially malicious instructions embedded within the extracted text from the PDF.
  • Capability inventory: The skill possesses the capability to write and generate Word documents using the moai-officer:doc-docx tool and may perform network lookups via the moai-analyst:data-public tool.
  • Sanitization: No explicit sanitization, escaping, or validation of the extracted PDF content is described before the data is interpolated into the analysis workflow or the final report template.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:42 PM
Security Audit — agent-trust-hub — consult-sbiz365