update-skills

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and merges code from an upstream Git remote (e.g., git fetch upstream --prune and listing upstream/skill/* branches, with a default https://github.com/qwibitai/nanoclaw.git) and reads/opens files and commits from those upstream branches, which are untrusted third‑party content that can influence merges, builds, and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill performs runtime git fetch/merge from an upstream repository (default URL https://github.com/qwibitai/nanoclaw.git), and the fetched repository content (skill branches) can directly change agent behavior/instructions by being merged into the running codebase.