request-fulfillment
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process data from external ServiceNow records which could contain malicious instructions.
- Ingestion points: Data is read from sc_req_item (fields: variables, short_description, description) and sc_task tables as shown in SKILL.md.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content within these fields.
- Capability inventory: The agent has the ability to write back to the system via SN-Update-Record and SN-Add-Work-Notes, potentially executing actions based on injected instructions.
- Sanitization: The procedure does not specify validation or sanitization steps for the data retrieved from ServiceNow fields.
Audit Metadata