incident-triage
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the native Bash tool to perform curl commands for interacting with ServiceNow REST API endpoints. This functionality is limited to standard operational tasks like querying incidents and updating record fields.
- [SAFE]: The skill identifies an indirect prompt injection surface as it processes user-controlled incident data. 1. Ingestion points: The skill reads 'short_description' and 'description' fields from ServiceNow incidents (SKILL.md, Step 1). 2. Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted content from the agent's instructions. 3. Capability inventory: The skill has tools to write data back to ServiceNow and execute shell commands (SKILL.md, Step 4 and 5). 4. Sanitization: No sanitization logic is present for the ingested incident data. This represents a low-level risk inherent to IT service management automation and is managed via standard agent safety protocols.
Audit Metadata