astropy
Warn
Audited by Snyk on Feb 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly supports accessing remote FITS files over HTTP/S3 and "query[ing] named objects from online databases," so it can fetch and ingest arbitrary public URLs/online data (untrusted third‑party content) that the agent would read and interpret as part of its workflow.
Audit Metadata