legalize-kr

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

• Third-party content exposure detected (high risk: 0.80). This skill's workflow and SKILL.md explicitly instruct the agent to fetch and read public third‑party content (e.g., git clone https://github.com/legalize-kr/... and the external https://legalize.kr/llms.txt or direct GitHub/raw URLs) so untrusted public data is ingested and can materially affect searches, tool calls, and outputs.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly instructs runtime fetching of external prompt/context content (e.g., https://legalize.kr/llms.txt) and using git clone (e.g., git clone https://github.com/legalize-kr/legalize-kr.git) so that remote Markdown data is injected into the agent/LLM context and thus directly controls prompts and is relied on for operation.