holmesgpt-skill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill includes examples that embed API keys/tokens directly in shell commands and CLI flags (e.g., export/ENV assignments, docker -e, and --pagerduty-api-key/--slack-token), which would require the model to handle or reproduce secret values verbatim if users supply them.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). The install command and raw_url point to a personal GitHub repo (zero stars) that instructs users to curl a raw file (and the repo likely contains scripts), which is an untrusted download source and a common malware distribution vector.

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 explicit installation and deployment commands (helm install, docker run with kubeconfig) and a Helm value createServiceAccount: true that would create Kubernetes resources/accounts—actions that modify cluster/machine state despite claiming read-only—which can change the environment the agent runs against.