ot-incident-resolution
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from ServiceNow incident records and journal fields, creating a potential surface for indirect prompt injection.
- Ingestion points: The
SN-Query-TableandSN-Get-Recordtools inSKILL.mdretrieve data from thesn_ot_incident(incident descriptions) andsys_journal_field(work notes) tables. - Boundary markers: The skill provides a structured resolution note template in Step 7, which helps maintain a boundary between data fields and the agent's summary instructions.
- Capability inventory: The skill's primary capabilities are focused on data retrieval and summary generation; it does not include tools for arbitrary command execution, file system writes, or network exfiltration based on the ingested content.
- Sanitization: There is no evidence of explicit sanitization or filtering of the retrieved record values before they are processed by the agent.
Audit Metadata