track-findings

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow searches and reads existing GitHub issues and pull requests, Jira tickets, Linear issues, and GitHub security advisories during duplicate checks and history gathering, exposing the agent to outsider-authored free text.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (medium risk: 0.30). The skill's purpose is tracking security findings in issue trackers (Linear, Jira, GitHub issues, and GitHub advisories) by creating or updating tickets and issues. This is an indirect financial operation (creating records/issues/tickets), which falls under the medium severity tier for indirect financial operations.