generic-crud-operations

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • [COMMAND_EXECUTION]: Provides examples for using the Bash tool to interact with the ServiceNow Table API via curl for querying and updating records.
  • [DATA_EXFILTRATION]: Performs network operations to interact with external ServiceNow instances (instance.service-now.com) to retrieve and manage record data. These operations target a well-known service for the skill's primary purpose.
  • [PROMPT_INJECTION]: A potential surface for indirect prompt injection exists when the agent processes untrusted data retrieved from ServiceNow tables.
  • Ingestion points: Data retrieved from ServiceNow records using SN-Query-Table, SN-Get-Record, and curl commands as described in SKILL.md.
  • Boundary markers: Absent; there are no instructions for using delimiters to distinguish external data from agent instructions.
  • Capability inventory: Shell command execution via the Bash tool and record modification capabilities via SN-Create-Record and SN-Update-Record tools as described in SKILL.md.
  • Sanitization: Absent; the skill does not include steps for sanitizing or validating external content before it is processed by the agent.
  • [NO_CODE]: The skill does not include any executable scripts or binaries, consisting solely of markdown instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 04:36 PM