itsm-suggested-steps
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 incidents and knowledge base articles to generate resolution steps, which could be manipulated to influence agent behavior.
- Ingestion points: The skill retrieves data from the
incidenttable (short_description, description, close_notes) andkb_knowledgetable (text) using theSN-Query-Tabletool (Steps 1, 2, and 3 in SKILL.md). - Boundary markers: The instructions do not define boundary markers (e.g., XML tags or clear delimiters) to separate the retrieved external data from the system instructions when generating the resolution plan.
- Capability inventory: The skill possesses write capabilities, including posting work notes to incident records via
SN-Add-Work-Notesand updating records viaSN-Update-Record(Steps 7 and 8 in SKILL.md). - Sanitization: There is no evidence of sanitization, filtering, or validation of the external content before it is processed by the model to generate the resolution steps.
Audit Metadata