server-connection-scala
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes the official and versioned Couchbase Scala SDK dependency (
com.couchbase.client %% scala-client % 1.7.0). - [SAFE]: The primary connection examples correctly demonstrate using environment variables (
sys.env) to retrieve sensitive credentials, avoiding hardcoded secrets in production code. - [SAFE]: A placeholder password ('Password!123') is used in a Capella connection example for illustrative purposes. This is identified as a documentation placeholder rather than a hardcoded credential leak.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it facilitates the ingestion of data from an external database into the agent's context.
- Ingestion points: Data is retrieved via
collection.getandcollection.lookupIninSKILL.mdandexamples/examples.md. - Boundary markers: No specific boundary markers or 'ignore' instructions are suggested for the data retrieved from the cluster.
- Capability inventory: The skill allows for high-privilege operations including
upsert,remove, andmutateIn. - Sanitization: No explicit sanitization or schema validation logic is demonstrated for the content retrieved from the database.
Audit Metadata