devops-troubleshooter
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze potentially untrusted external data sources, creating a surface for indirect prompt injection attacks.
- Ingestion points: The skill explicitly instructs the agent to gather and assess data from logs, metrics, distributed traces, and system state (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or instructions for the agent to distinguish between data and commands when processing these external logs.
- Capability inventory: The skill encourages the use of high-privilege diagnostic and management tools, including kubectl for Kubernetes, network analysis tools (tcpdump, dig), and Infrastructure-as-Code tools (Terraform, Ansible).
- Sanitization: There are no instructions provided for sanitizing, escaping, or validating the external content before the agent processes it.
Audit Metadata