implementing-zero-trust-with-hashicorp-boundary

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill embeds literal secret values (e.g., database password and AEAD keys) and secrets blocks in configuration files, which would require the LLM to reproduce secret values verbatim in generated configs/outputs, creating an exfiltration risk.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.90). The skill includes explicit sudo installation commands and configuration that writes to /etc (system service/config files and TLS keys), which instructs privileged changes to the host system.