insforge-debug

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes explicit CLI patterns that fetch and set secrets (e.g., npx @insforge/cli secrets get <key> and npx @insforge/cli secrets add <key> <value>), which require handling secret values and even passing them as command-line arguments, creating a direct exfiltration risk if the LLM outputs them verbatim.