prompt-engineering-library

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to "Use web search to find the latest news and resources" (Hallucination Management Gate) and to learn from or match external "URL, competitor post, or LinkedIn profile" (Prompt Component #9 and multiple templates requesting external links), which requires ingesting untrusted public web/user-generated content that could influence subsequent prompting or actions.