remotion-video

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 "GitHub Repo (Deep Scan)" workflow explicitly clones/fetches user-supplied public GitHub repositories and reads README.md, package.json, src/, docs/, etc., which are untrusted third-party/user-generated contents that the agent parses to infer a ProductProfile and drive script/code generation—allowing injected instructions in repo files to materially influence the agent's outputs and actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly clones a user-provided GitHub repo at runtime (via "gh repo clone" / "git clone" of the GitHub repo URL) and uses the fetched repository contents to generate the VideoScript, so a remote repo URL can directly control the agent's prompts/instructions.