pp-printing-press-rich

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt shows and instructs using verbatim secrets in shell commands (export RICH_AUTH_API_KEY="") and passing tokens as CLI arguments (printing-press-rich-pp-cli auth set-token ), which would require the agent/LLM to handle and emit secret values directly.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). These links mainly point to GitHub repos and a GitHub release that distribute pre-built CLI/binary artifacts from individual/smaller accounts (plus a placeholder API URL), and GitHub releases/personal repos carrying unsigned executables are a common malware-distribution vector unless you can verify the author and artifact signatures—so treat as suspicious.

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via runtime API responses: the MCP/CLI “items”/“search”/“sql” tools fetch live JSON from the configured Rich Auth API and return it (including any upstream message/body text) into the agent’s tool result, which the agent then places into its LLM context.