sn-update

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly clones/syncs the public upstream repo https://github.com/OpenSenseNova/SenseNova-Skills.git (and optionally user-specified fork URLs) and copies those third-party skill trees into the agent's skills directory per the "Sync the upstream repo" and "Install with backup" steps in SKILL.md, meaning untrusted repository contents (arbitrary skill code/files) are fetched and installed and can directly change agent behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches and installs runtime agent skills from the upstream Git repository (https://github.com/OpenSenseNova/SenseNova-Skills.git), so content downloaded at runtime can change agent prompts/instructions or deliver executable skill code.