incident
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructional content and markdown templates for incident management (SEV-1 to SEV-4). It includes standard workflows and communication templates without any executable scripts or hidden commands.- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to process external incident descriptions provided by users or log data. However, since the skill only provides formatting templates and guidance to the agent, the risk is considered safe within its intended functionality. The following evidence chain was evaluated:
- Ingestion points: Incident descriptions passed as arguments to the
/incidentcommand. - Boundary markers: None explicitly defined in the templates.
- Capability inventory: The skill is limited to standard file operations (Read, Write, Grep, Glob) as defined in the allowed-tools metadata.
- Sanitization: Not applicable for template-based output.
Audit Metadata