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