cnb-token

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill asks the user to paste their Personal Access Token to the agent and then instructs embedding that token verbatim into commands like setx/export (e.g., setx CNB_TOKEN ""), which requires the LLM to receive and output secret values directly.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill explicitly instructs users to paste their Personal Access Token to the assistant and persist it via environment variables and a git credential helper, which is direct collection of credentials and poses a high risk of credential theft or exfiltration if misused.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The skill explicitly asks the user to paste a Personal Access Token into the agent and then persist it into the user environment (setx/export) and global git config (credential helper), which changes the machine's persistent state and stores sensitive credentials—though it does not request sudo or system-level changes.