open-thread

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

• Third-party content exposure detected (high risk: 0.75). In Mode B, the workflow explicitly “read[s] the ticket (title + body)” from an external tracker at runtime and uses that ticket text to seed the trigger narrative in seed/seed.md, which is then ingested into the agent’s LLM context as free-form text (indirect prompt-injection risk).