google-local-services-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill requires a FREVANA_TOKEN and explicitly permits passing it via a --token command-line argument, which encourages including secret values in commands/outputs and thus risks secret exfiltration.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required workflow sends a user-supplied query to Frevana and then reads the outsider-controlled HTTP response body (JSON text) from scripts/search_google_local_services.sh into stdout via cat "$RESULT_FILE", which is then returned unchanged to the agent/LLM context.