rug-checker

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

• Third-party content exposure detected (high risk: 1.00). The skill directly fetches and ingests public, untrusted data from api.rugcheck.xyz and api.dexscreener.com (see scripts/common.sh and analyze-risk.sh which call rugcheck_report/dex_token and then use that data to compute composite scores and report tiers), so third-party content is read and can materially influence the agent's outputs.