gke-cluster-config
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and metadata do not contain any malicious patterns, obfuscation, or attempts to access sensitive data.
- [NO_CODE]: There are no scripts, binaries, or automated installation processes included in this skill.
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with user-provided triggers and has access to system capabilities, creating an attack surface for indirect prompt injection.
- Ingestion points: User prompts triggered by keywords 'gke cluster config', 'gke config', or 'gke' as defined in SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the text.
- Capability inventory: The skill is configured to use Read, Write, Edit, and Bash(gcloud:*) tools.
- Sanitization: No input validation or sanitization logic is specified within the instructions.
Audit Metadata