mdadf-cli

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

• Third-party content exposure detected (high risk: 1.00). The skill's required install flow (references/commands.md) instructs the agent to fetch and execute installer scripts from raw.githubusercontent.com (e.g., "curl ... | sh" and "irm ... | iex"), which are public, user-controlled third‑party resources that the agent would ingest/execute and could therefore materially change its behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill includes runtime install commands that fetch and execute remote scripts (curl -fsSL https://raw.githubusercontent.com/chenhunghan/mdadf/main/install.sh | sh and irm https://raw.githubusercontent.com/chenhunghan/mdadf/main/install.ps1 | iex), which run untrusted remote code as a required dependency if mdadf is missing.