deepseek-researcher

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

• Third-party content exposure detected (high risk: 1.00). The skill's §5 platform instructions explicitly tell the agent to "Read [URL] and install as skill" using a public raw GitHub URL (https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/enterprise/deepseek/deepseek-researcher/SKILL.md), which requires fetching and ingesting untrusted third-party content that can change the agent's behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly tells platforms to "Read [URL] and install as skill" pointing to https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/enterprise/deepseek/deepseek-researcher/SKILL.md, meaning the agent would fetch remote content at runtime that contains the system prompt/instructions which directly control agent behavior and is required for installation.