doc-core-api

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill describes a runtime environment in the WPS Plugin Host that uses new Function() to execute code generated by the agent.
  • [PROMPT_INJECTION]: The skill facilitates reading untrusted content from the active document, which serves as a vector for indirect prompt injection.
  • Ingestion points: Document content accessed via Application.ActiveDocument, Selection.Text, and Range.Text.
  • Boundary markers: No delimiters or instructions are specified to prevent the agent from following commands embedded in the document text.
  • Capability inventory: The agent can read, modify, and delete document content, tables, and sections.
  • Sanitization: There are no instructions for sanitizing or escaping content retrieved from the document before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 04:55 PM
Security Audit — agent-trust-hub — doc-core-api