copilot-review

Warn

Audited by Snyk on Jun 22, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). The required workflow ingests PR discussion text via gh pr view <number> --json reviews,reviewThreads,comments (including review comments/threads authored by outsiders), and the LLM then processes that free-form comment body text before filtering—so outsider-authored text can enter the agent context indirectly through the mandatory GH query collection step.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 22, 2026, 05:54 AM
Issues
1
Security Audit — snyk — copilot-review