setup-work-skills

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). scripts/install.sh clones and copies files from a third‑party GitHub repo (https://github.com/kenlck/skills.git) into the local project—pulling and installing code from an individual/unverified GitHub account is a potential malware distribution vector.

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

• Third-party content exposure detected (medium risk: 0.30). In the required workflow for $do-work/$do-seo-work, the agent reads free text from outsider-authored GitHub issue/PR content (issue bodies, comments, thesis/research links, testing decisions, and work-package contract surfaces) and can be driven by queue selection of “ready-for-agent/ready-for-seo-agent”.

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

• Potentially malicious external URL detected (high risk: 1.00). The installer (scripts/install.sh) performs a runtime git clone of https://github.com/kenlck/skills.git and copies SKILL.md files from that repo into the project, meaning remote content fetched from that URL directly controls agent skill prompts and is a required dependency.