audit-compliance
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill utilizes the
SN-Execute-Background-Scripttool to perform complex analysis and compliance reporting. This involves executing arbitrary JavaScript code on the ServiceNow server, which is a high-privilege administrative capability intended for audits and troubleshooting. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from ServiceNow logs and audit tables, creating a vulnerability surface where malicious data could influence agent behavior.
- Ingestion points: The skill ingests untrusted data from the
sys_audit,syslog,sysevent, andv_user_sessiontables usingSN-Query-TableandSN-Execute-Background-Script(SKILL.md). - Boundary markers: The instructions do not define boundary markers or specify that the agent should ignore instructions embedded within the processed audit records.
- Capability inventory: The environment includes tools with high impact, specifically
SN-Execute-Background-Script(arbitrary code execution),SN-Create-Record(database write access), andSN-Query-Table(database read access). - Sanitization: The skill does not implement sanitization, filtering, or validation of the log content before the agent processes or summarizes the data.
Audit Metadata