alterlab-ena

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

• Third-party content exposure detected (high risk: 0.90). This skill programmatically fetches and ingests public, user-submitted ENA data (e.g., via the ENA Portal and Browser APIs at https://www.ebi.ac.uk/ena/portal/api and https://www.ebi.ac.uk/ena/browser/api and via public FTP like ftp.sra.ebi.ac.uk) and the documentation explicitly instructs the agent to read/parse those XML/JSON/TSV responses and use extracted accessions/URLs in downstream pipeline actions, so untrusted third-party content can materially influence behavior.