santiment-api

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt tells the agent to ask the user for their API key if no $SANTIMENT_API_KEY is set and to execute curl requests using the user's API key in the Authorization header, which forces the LLM to receive and potentially emit the secret verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow (scripts/santiment_query.py → build_query/execute_query) ingests outsider-authored JSON fields (notably metric, slug/slugs, selector, transform, from/to, etc.) from stdin provided by the caller and sends them as GraphQL variables to https://api.santiment.net/graphql.