AGENT LAB: SKILLS

docker

Fail

Audited by Snyk on Feb 15, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.90). The prompt contains multiple examples that embed plaintext credentials directly into commands and compose files (e.g., POSTGRES_PASSWORD: secret, DATABASE_URL with embedded password, echo "db_password_here" | docker secret create), which instructs including secret values verbatim in generated configs/commands and thus creates an exfiltration risk.

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

  • Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill includes privileged host commands (e.g., "sudo systemctl restart docker", "sudo usermod -aG docker $USER") that modify host system state and user/group membership, which requires elevated privileges and can change the machine's state.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 08:11 PM