instance-management
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external ServiceNow instances, which constitutes a potential surface for indirect prompt injection attacks where instructions could be embedded in database records.
- Ingestion points: Data is ingested from ServiceNow via the
SN-Query-Tabletool (SKILL.md). - Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions embedded within the retrieved data.
- Capability inventory: The skill provides tools for state-changing operations including
SN-Create-Record,SN-Update-Record, and local shell access viaBash(SKILL.md). - Sanitization: The skill does not specify sanitization or validation logic for the data returned from ServiceNow queries before it is used in further logic.
Audit Metadata