physical-ai-neural-reconstruction

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow reads outsider-authored free text from the upstream GitHub repository by executing cat "$UPSTREAM_ROOT/nurec-skills/.agents/skills/SKILL.md" (and sibling SKILL.md files), which are not authored by the operating user.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly runs git fetch/clone/pull at runtime to retrieve https://github.com/NVIDIA/nurec-skills (e.g., git clone https://github.com/NVIDIA/nurec-skills.git) and then instructs agents to read and follow the upstream SKILL.md, so remotely-fetched content directly controls agent instructions and is a required dependency.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill explicitly recommends running a sudo command to change file ownership ("sudo chown -R ..."), which instructs elevated privileges and mutates system state after Docker usage.