webex-incident-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
python3to execute integration scripts for ServiceNow and GAIT. These scripts are invoked using paths provided by environment variables ($SERVICENOW_MCP_SCRIPTand$GAIT_MCP_SCRIPT), which is a standard pattern for MCP-based tool interaction. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which could lead to indirect prompt injection if an attacker can control log output or webhook data.
- Ingestion points: The skill ingests network device logs (e.g.,
R2 logsin Phase 3) and processes data from WebEx Adaptive CardAction.Submitwebhooks. - Boundary markers: No explicit delimiters or boundary markers are used to isolate untrusted data when it is interpolated into status updates or shared in WebEx spaces.
- Capability inventory: The skill possesses capabilities to execute local Python scripts, create WebEx spaces, manage memberships, and post automated messages.
- Sanitization: The skill does not describe any sanitization or validation logic for the external log data or webhook payloads before processing or displaying them.
Audit Metadata