decompose-task
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: 0.90). The skill explicitly fetches and parses issue content from external issue trackers (mcp_atlassian_getJiraIssue for Jira and mcp_github_issue_read for GitHub) and reviews attached/linked documents, which are untrusted, user-generated third-party sources that the agent reads and interprets as part of its workflow.
Audit Metadata