work-on-issue

Warn

Audited by Snyk on Jul 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: 0.85). SKILL.md Step 2 spawns an issue-worker subagent with a prompt to “Read GitHub issue #…”, so the agent will ingest outsider-authored GitHub issue body text at runtime and feed extracted requirements back into the main agent’s LLM context.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 8, 2026, 04:16 AM
Issues
1
Security Audit — snyk — work-on-issue