team-setup

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

• Third-party content exposure detected (low risk: 0.10). Source and runtime path: outsider-authored free text is only accepted via user-provided inputs (e.g., GitHub clone URL / local path / team name) or is subsequently read from repositories or local directories that the user explicitly points to, rather than from an unsolicited external feed/queue the workflow passively monitors.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill executes a runtime git clone of a user-supplied GitHub URL (default shown as https://github.com/tikalk/agentic-sdlc-team-ai-directives) and the cloned repository is later read by agents to load directives (i.e., it can directly control prompts), so this external URL is a runtime dependency that can influence agent instructions.