acceptance-criteria
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash native tool to perform REST API operations (GET and PATCH) against ServiceNow table endpoints for reading and updating story records.
- [PROMPT_INJECTION]: The skill processes external data from ServiceNow records to generate acceptance criteria, which introduces an indirect prompt injection surface.
- Ingestion points: Data is retrieved from the
description,short_description, andacceptance_criteriafields of therm_storyandrm_epictables (Step 1, Step 2, and Step 7). - Boundary markers: Absent; the instructions do not implement delimiters or warnings to ignore instructions that might be embedded in the retrieved ServiceNow data.
- Capability inventory: The skill has write access via the
SN-Update-Recordtool and Bash-based REST PATCH requests, allowing it to modify records based on processed data. - Sanitization: No explicit sanitization or validation of the ingested record content is performed before interpolation into the generation prompt.
Audit Metadata