alterlab-pubmed
Warn
Audited by Snyk on Apr 12, 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 instructs the agent to fetch and parse public third-party content from PubMed via the E-utilities REST API (e.g., SKILL.md and references/api_reference.md describe using esearch/efetch to download abstracts and records), so the agent will read and act on untrusted external webpages/records that could contain instructions or influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata