civic-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill issues GraphQL queries to the public CIViC endpoint (https://civicdb.org/api/graphql) via scripts/civic_graphql.py and returns compact summaries of that remote, community-curated data as part of its normal workflow, so untrusted third-party content can be read and influence the agent's actions.