cite

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to "Fetch each URL and extract metadata" from public paper links (e.g., arXiv, DOI, conference URLs shown in README/usage), meaning it ingests untrusted third‑party web content and uses that content to determine citations and next actions, enabling indirect prompt injection.