search-paper
Warn
Audited by Snyk on Apr 17, 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's required workflow (SKILL.md and references/USAGE.md) instructs running search-paper-cli commands like "search" and "get --as text|pdf" which fetch papers and extracted text from public third‑party sources (e.g., arXiv, Semantic Scholar, Unpaywall and arbitrary paper URLs), so the agent will ingest untrusted external content that could contain instructions influencing subsequent actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill's runtime install helper can fetch and execute remote code — it uses
go install github.com/jtsang4/search-paper-cli/cmd/search-paper-cli@latestand downloads release artifacts from URLs like https://github.com/jtsang4/search-paper-cli/releases/latest/download/, thereby installing and running externally fetched binaries.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata