upstream-sync

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

• Third-party content exposure detected (high risk: 0.90). The skill's sync_upstream.py explicitly clones and reads arbitrary public GitHub repos listed in upstream_registry.json (see clone_repo and the sync_* handlers that read README/SKILL.md and other files) and uses that untrusted repository content to decide updates, create branches, and overwrite local files—allowing third-party content to materially influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The sync script clones upstream GitHub repos at runtime (e.g., https://github.com/techwavedev/prompts.git) and those repos contain system prompt/skill markdown that, when merged into the codebase, directly control agent prompts/instructions—constituting a required runtime dependency.