deepmind-researcher

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

• Third-party content exposure detected (high risk: 0.90). The skill's Platform Support (§5) explicitly instructs agents to "Read [URL] and install as skill" pointing to the public raw GitHub URL (https://raw.githubusercontent.com/theneoai/awesome-skills/.../SKILL.md), which means the agent would fetch and ingest untrusted, user-editable third‑party content as runtime skill/system-prompt material and thus is vulnerable to indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs platforms to "Read [URL] and install as skill" where [URL] is https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/enterprise/deepmind/deepmind-researcher/SKILL.md — fetching that raw GitHub file at install/runtime would supply the system prompt and instructions that directly control the agent.