activity-response
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from several ServiceNow tables.
- Ingestion points: Customer communications in
sys_email(Step 5), case descriptions insn_customerservice_case(Step 1), and journal entries insys_journal_field(Step 2). - Boundary markers: While the skill uses headers like '=== WORK NOTE ===', it lacks explicit instructions to the model to ignore any embedded directives within the retrieved data.
- Capability inventory: The skill utilizes the 'Bash' native tool and has access to multiple ServiceNow table APIs for reading and writing data.
- Sanitization: There is no evidence of sanitization, escaping, or validation performed on the external content before it is interpolated into the response templates.
Audit Metadata