gh-agent-session

Warn

Audited by Snyk on Mar 18, 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 ingests and acts on user-generated GitHub issue content (e.g., workflows that trigger "When an issue is labeled..." and the agent-session issue descriptions used by gh agent-task) so arbitrary public issue text can be read and used to drive Copilot agent actions and PR creation.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 01:16 PM
Issues
1