credential-sync

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly reads local credential files (e.g., .env, credentials.json), builds a files dictionary containing their plaintext contents, and instructs injecting those contents (and printing the encryption key) verbatim in mcp__trinity__inject_credentials / outputs, which requires the LLM to handle secret values directly.