tprm-issue-summarization

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill instructions or provided scripts.
  • [DYNAMIC_EXECUTION]: The skill utilizes ServiceNow's background script execution capability to perform complex data aggregations and remediation analysis. These scripts are static, scoped to data retrieval and processing within the ServiceNow instance, and do not incorporate untrusted external input into the execution flow.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from ServiceNow tables (such as issue descriptions and vendor assessments) which may contain untrusted user-generated content.
  • Ingestion points: Data is retrieved from the sn_tprm_issue and sn_tprm_vendor_assessment tables (SKILL.md).
  • Boundary markers: The summary output template for work notes does not explicitly use boundary delimiters to isolate the summarized content.
  • Capability inventory: The skill has the capability to execute background scripts and write to ServiceNow records using SN-Add-Work-Notes.
  • Sanitization: There is no explicit sanitization of the retrieved text before it is summarized or posted back to the platform. However, this is consistent with the primary purpose of a summarization skill, and the risk is considered low.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:23 PM
Security Audit — agent-trust-hub — tprm-issue-summarization