smart-documents

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection as it ingests and processes data from external document records and attachments.
  • Ingestion points: Data is retrieved from the sn_doc_management, sn_doc_template, and sys_attachment tables via SN-Read-Record, SN-Query-Table, and REST API calls.
  • Boundary markers: The skill instructions do not define boundary markers or provide the agent with directives to ignore instructions potentially embedded in the document content.
  • Capability inventory: The agent has access to tools for creating and updating records (SN-Create-Record, SN-Update-Record) and executing shell commands via Bash for REST API interactions.
  • Sanitization: There is no evidence of sanitization, filtering, or validation performed on the external data before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill is configured to use the Bash native tool specifically for executing curl commands to interact with the ServiceNow REST API for document management tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:24 PM
Security Audit — agent-trust-hub — smart-documents