doe-osti

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly queries and ingests public OSTI records from https://www.osti.gov/api/v1/records (see SKILL.md and references/python_example.py), parses titles/abstracts/links and uses those results to drive pagination, produce summaries, and follow fulltext links—i.e., it consumes untrusted third-party content as part of its workflow.