k8s-manifest-generator
Fail
Audited by Snyk on Mar 3, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (high risk: 1.00). The prompt contains a "Memory Protocol (MANDATORY)" that instructs the agent to read and write local filesystem memory files and enforce persistent agent behavior, which is unrelated to generating Kubernetes manifests and constitutes an out-of-scope instruction that alters agent behavior and could exfiltrate state—i.e., a prompt-injection.
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to create Kubernetes Secret resources and includes templates with literal secret fields (e.g., DATABASE_PASSWORD, API_KEY) and prompts about "are there any secrets..." which would require the model to accept and embed secret values verbatim in generated YAML, creating exfiltration risk.
Audit Metadata