azure-integration-tester

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow and scripts (e.g., SKILL.md usage examples and scripts/test-function-app.sh, scripts/test-storage.sh, scripts/test-database.sh) explicitly fetch and inspect HTTP endpoints, storage blob contents, and database responses from arbitrary user-provided Function App URLs, storage accounts, and other endpoints—untrusted third-party content that the agent reads and uses to make pass/fail decisions and follow-up actions.