agent-repair

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to read and "show you the current values" of environment variables and to "check and update API keys or credentials," which requires exposing secret values verbatim in outputs or commands.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly directs the agent to perform Phase 2 repairs that edit configuration files, change permissions, restart services, install packages and run shell commands — all actions that modify system state and can require sudo or affect security-critical files.