chinese-thesis-workbench

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: 0.70). The skill's material-gap-handoff workflow and README explicitly state that, with user consent, the agent will perform web searches ("联网检索") for same-field literature and write candidates into paper-context/literature/web-suggested.md (see references/workflow/material-gap-handoff.md and README "素材稀缺处置"), meaning it fetches and ingests untrusted public web content that the agent will read and that can influence outline/content decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 8, 2026, 08:01 AM
Issues
1