jira

Warn

Audited by Snyk on Feb 26, 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.md explicitly instructs the agent to fetch Jira data via the Maton gateway (e.g., GET /jira/ex/jira/{cloudId}/rest/api/3/search/jql and GET /.../issue/{issueIdOrKey}/comment), which pulls user-generated/untrusted issue summaries and comments that the agent is expected to read and can materially influence subsequent actions like transitions, updates, or searches.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 26, 2026, 10:28 AM