paper-summary
Warn
Audited by Snyk on Mar 2, 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 requires fetching/reading paper content from a URL or DOI ("Summarise an academic paper: $ARGUMENTS (URL, DOI, or file path)" and Step 1 "Fetch/read the paper content"), so the agent ingests external third‑party content that can directly influence its summaries and downstream decisions.
Audit Metadata