product-data-import

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of processing untrusted external data.
  • Ingestion points: According to SKILL.md, the skill accepts raw input from various sources including notes, pasted spreadsheets, CSV files, and conversational text. It also explicitly supports reading from user-provided file paths.
  • Boundary markers: The skill instructions do not define any delimiters or system-level instructions to the agent to ignore or isolate potential commands embedded within the product data being processed.
  • Capability inventory: The skill has access to high-privilege tools including Bash, Write, Edit, and Google Sheets MCP integration tools (mcp__google-sheets__update_cells, mcp__google-sheets__get_sheet_data).
  • Sanitization: There is no evidence of input validation, escaping, or sanitization of the raw product data before it is processed or passed to the output tools.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 11:58 AM
Security Audit — agent-trust-hub — product-data-import