biomedical-literature-search

Warn

Audited by Snyk on Mar 25, 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). This skill programmatically fetches and ingests abstracts and metadata from public, user-authored sources (PubMed via NCBI E-utilities and bioRxiv via the bioRxiv API as shown in SKILL.md and examples/basic_example.py), which the agent reads and can use to drive its outputs and decisions, creating a clear vector for indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 25, 2026, 05:56 AM
Issues
1