use-native-credential-proxy

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly reads secrets from .env and returns Docker "-e VAR=value" arguments (e.g., injecting ANTHROPIC_API_KEY / CLAUDE_CODE_OAUTH_TOKEN verbatim into container args), which requires the agent to handle and could cause it to output secret values verbatim, creating a high exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This skill intentionally and explicitly bypasses the secure OneCLI agent vault and reads Anthropic credentials from a host .env to inject them as Docker -e environment variables into containers, creating a deliberate and high-risk secret-exposure vector that could be abused for credential theft or downstream data exfiltration.