devops-troubleshooter
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of processing untrusted data from external monitoring and logging systems.
- Ingestion points: Processes untrusted content from logs (ELK, Loki), metrics (Prometheus), and distributed traces (Jaeger) as defined in SKILL.md.
- Boundary markers: Absent; the instructions do not include delimiters or specific guidance to ignore instructions embedded within the data being analyzed.
- Capability inventory: The persona is designed to use powerful administrative tools including kubectl, AWS/Azure/GCP CLIs, and various network analysis tools.
- Sanitization: No protocols for data sanitization, input validation, or filtering of external content are mentioned in the troubleshooting instructions.
Audit Metadata