ise-incident-response

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses python3 $MCP_CALL to execute commands that include script paths defined in environment variables such as $ISE_MCP_SCRIPT, $SERVICENOW_MCP_SCRIPT, and $GAIT_MCP_SCRIPT. This creates a dynamic execution path where the agent's behavior depends on the content and location of external scripts.
  • [CREDENTIALS_UNSAFE]: Authentication credentials ($ISE_USERNAME and $ISE_PASSWORD) are passed as environment variables within a command-line string. This practice can potentially expose credentials in system process logs or process monitors.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks (Category 8) as it processes data from external network services.
  • Ingestion points: Data enters the agent's context through tools like endpoints, active_sessions, and network_access_authorization_rules (file: SKILL.md).
  • Boundary markers: The skill provides a structured template for the 'ENDPOINT INVESTIGATION SUMMARY' but lacks explicit delimiters or instructions to ignore embedded commands within the retrieved network data.
  • Capability inventory: The skill possesses the ability to modify endpoint group memberships in ISE, create and comment on ServiceNow incidents, and record audit trails in GAIT.
  • Sanitization: There are no explicit instructions for the agent to sanitize or escape data retrieved from ISE before using it in the 'Risk Assessment' or ServiceNow incident descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 12:31 AM