runbook-creation
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily a collection of markdown templates. The identified shell commands (e.g., kubectl, psql, aws CLI) are intended as examples for operational documentation and are not part of any malicious execution chain. External links point to well-known and trusted industry resources such as PagerDuty and Google SRE.- [PROMPT_INJECTION]: The skill structure for generating runbooks creates a potential surface for indirect prompt injection.
- Ingestion points: User input defining incident details and infrastructure components processed through SKILL.md and reference templates.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included in the generated output templates.
- Capability inventory: Generation of documentation containing high-privilege commands for cluster and database management.
- Sanitization: No sanitization is performed on the input strings used to populate the runbook templates.
Audit Metadata