refine-issue-plan

Warn

Audited by Snyk on Aug 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: 0.30). In SKILL.md, the skill explicitly instructs the agent to read the complete outsider-authored issue body, comments, and linked attachments/metadata (and current conversation) in order to plan (Resolve the task steps 14-15), making injection possible via tracker contents fed into the workflow.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 25, 2026, 08:56 AM
Issues
1
Security Audit — snyk — refine-issue-plan