paper-analysis

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Paper Acquisition" steps explicitly fetch content from public third-party sources (e.g., https://doi.org/DOI, Semantic Scholar API, https://arxiv.org/abs/ID, and arbitrary URLs via web_fetch), which the agent ingests and analyzes as part of its workflow, exposing it to untrusted user-generated or public web content that could carry indirect prompt-injection.