adr-summarization

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its core functionality of summarizing text from external sources (ServiceNow ADRs).
  • Ingestion points: Free-form text is ingested from the sn_ea_architecture_decision_record table (context, decision, rationale, and consequences fields) via SN-Query-Table and SN-Get-Record tools.
  • Boundary markers: The instructions do not define specific delimiters to separate record content from agent instructions.
  • Capability inventory: The agent has write access to ServiceNow through SN-Update-Record and SN-Create-Record, and access to the local environment via the Bash tool.
  • Sanitization: No explicit sanitization or filtering of the ingested content is performed. This surface area is considered standard and safe for the intended governance use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:24 PM
Security Audit — agent-trust-hub — adr-summarization