github-workflow
Warn
Audited by Snyk on Feb 15, 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). This skill explicitly fetches task content via data-source commands and find-skills in Step 1 (e.g., running commands.get / commands.comments for ClickUp/Jira/Notion or using find-skills on user-provided URLs) to retrieve titles, descriptions and comments from external task platforms, so the agent ingests untrusted, user-generated third-party content.
Audit Metadata