paper-fetcher-vp

Warn

Audited by Snyk on Aug 11, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). SKILL.md “Core Workflow” step 2 (“Search online when needed and verify…”) and step 5 (“Download the official PDF…”) means outsider-authored user text can supply arbitrary paper identifiers/URLs that drive the agent to fetch and LLM-ingest external page/PDF content at runtime.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 11, 2026, 01:32 AM
Issues
1