pr-risk-scoring

Warn

Audited by Snyk on Mar 21, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md process explicitly instructs running gh pr list, gh pr diff <number> --name-only, and gh pr view --json reviews to ingest GitHub PR metadata, file lists, labels and reviews (user-generated, untrusted third-party content), and those inputs are directly used by score_prs.py to compute risk scores and assign tiers/labels that drive follow-up actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 21, 2026, 06:35 AM
Issues
1
Security Audit — snyk — pr-risk-scoring