dspy-langtrace

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

• Third-party content exposure detected (high risk: 0.80). This skill's required workflow instructs viewing traces at the third-party dashboard (e.g., "View traces at app.langtrace.ai" in SKILL.md) and explicitly exposes a "Prompt/response viewer: full text of every LM interaction" (and includes fetching the Langtrace repo), so the agent would read and act on untrusted, user-generated third-party content that could influence decisions.