Asta Literature Search

Warn

Audited by Snyk on May 8, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs running the asta literature find and asta papers (Semantic Scholar) commands to fetch and index search results, paper abstracts/snippets, and citation contexts from public academic websites, which the agent is then told to read and extract relevance criteria from—exposing it to untrusted third‑party content that can influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 8, 2026, 12:04 AM
Issues
1