claude-code-tips-productivity

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). These links include direct .sh raw GitHub scripts (high-risk to curl|bash from an unfamiliar user), a Gumroad download (personal file hosting for binaries), and several small/opaque domains/repos that are not established official vendors — collectively making them moderately to highly risky to download/execute without review or sandboxing.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs fetching and ingesting public web content (e.g., using Gemini CLI: gemini "Search for latest React documentation..." > gemini-output.txt and downloading/executing scripts from raw.githubusercontent.com like curl -o ~/.claude-status.sh https://raw.githubusercontent.com/.../context-bar.sh and curl ... | bash), so the agent is expected to read untrusted, third‑party content that could materially influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes commands that fetch and execute remote scripts at setup/runtime—notably https://raw.githubusercontent.com/ykdojo/claude-code-tips/main/quick-setup.sh (used with curl | bash) and https://raw.githubusercontent.com/ykdojo/claude-code-tips/main/scripts/context-bar.sh (curl then chmod +x and run)—which will execute remote code and can directly affect the agent environment and behavior.