feedback-summarization

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection attacks because it ingests and processes untrusted user-contributed text from ServiceNow records.\n
  • Ingestion points: Data is retrieved from rm_sprint (retrospective_notes), asmt_assessment_instance_question (string_value), and sys_journal_field (work_notes).\n
  • Boundary markers: Absent; there are no delimiters or instructions provided to the agent to treat the retrieved text as untrusted data.\n
  • Capability inventory: The skill has access to SN-Execute-Background-Script, SN-Create-Record, and Bash.\n
  • Sanitization: No sanitization or escaping is performed on the ingested text before it is analyzed or used in script logic.\n- [REMOTE_CODE_EXECUTION]: The skill leverages the SN-Execute-Background-Script tool to run server-side JavaScript templates for data aggregation. Although the provided scripts are static templates, the availability of this tool allows for powerful execution within the ServiceNow instance.\n- [COMMAND_EXECUTION]: Documentation includes Bash examples using curl to interact with standard ServiceNow REST API endpoints for data retrieval purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:24 PM
Security Audit — agent-trust-hub — feedback-summarization