generate-cases

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

• Third-party content exposure detected (high risk: 0.85). Step 1 explicitly instructs the agent to gather “information sources” from outsider-authored artifacts (e.g., Jira/Confluence pages, design mockups, existing test cases, and especially Testomat.io content via MCP or sync-cases), which at runtime can be ingested as readable text into the agent’s LLM context.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)