copilot-coding-agent
Warn
Audited by Snyk on Feb 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: 0.90). The skill automatically assigns Copilot to GitHub Issues and has the Actions/GraphQL workflow read and act on issue content (see "Step 3: 워크플로 동작 방식" and "Step 4: 이슈 라벨링" in SKILL.md), meaning untrusted, user-generated GitHub issue text can be ingested and directly influence code-generation and subsequent tool actions.
Audit Metadata