reference-module

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly adds arbitrary external git repositories via "git submodule add " (steps 2–4) and instructs the agent to read the submodule contents for research, which causes the agent to fetch and interpret untrusted, user-generated third‑party repository content.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill adds arbitrary git repositories at runtime via commands like "git submodule add " (example install URL: https://github.com/Skarian/codex-skills/tree/main/project) and then reads the fetched submodule contents for "research", meaning remote repository content is fetched at runtime and injected into the agent's context, which can directly control prompts/responses.