basilica

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The examples explicitly show embedding an API token in an env export and in client code (export BASILICA_API_TOKEN="basilica_..." and BasilicaClient(api_key="basilica_...")), which instructs the agent to include secret values verbatim in commands/code.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). Suspicious — the skill instructs piping a raw shell script (https://basilica.ai/install.sh) into bash from a single domain rather than a trusted package manager or well-known vendor; executing unverified .sh files from an unverified domain is a common malware vector.