helm-chart-scaffolding

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The "Memory Protocol (MANDATORY)" section instructs the agent to read and write local memory files (via a shell command and explicit paths) and to persist decisions outside the Helm-chart-scaffolding purpose, which is a hidden/deceptive instruction that alters agent behavior and side effects unrelated to the skill's stated function.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs using external chart repositories and commands that fetch remote charts (e.g., "Manage Dependencies" and "Package and Distribute" steps with helm dependency update, helm repo add https://charts.example.com and references to https://charts.bitnami.com/bitnami and GitHub sources), which causes the agent/tooling to ingest untrusted, public third‑party chart content (templates/hooks/NOTES) that can influence installs and subsequent actions.