executing-tasks-from-any-source

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). This skill fetches and parses GitHub issue content using commands like "gh issue view $ISSUE_NUM" (GitHub issues are user-generated/untrusted third-party content) and then directly reads/interprets that content as part of its workflow, exposing the agent to possible indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:04 AM