research

Warn

Audited by Snyk on Jul 25, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.65). The required workflow captures stdout from “research agents” into research/raw/<thread>.md and then the orchestrating agent assembles that verbatim outsider-authored free text into research.md, which is later loaded by /design//plan//phase-plan into the LLM context.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 25, 2026, 01:12 PM
Issues
1
Security Audit — snyk — research