indices

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). The set includes a direct installer script (https://indices.io/install.sh) explicitly recommended to be fetched and piped to bash ("curl ... | bash"), which is a high-risk pattern for malware delivery even if the other links are ordinary web pages (platform.indices.io and example domains); unverified remote .sh executables and instructions to run them make this collection suspicious.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to reach and interact with arbitrary websites (see "When To Use" and the indices tasks create --website examples and the platform.indices.io/tasks/{task_id} demo flow), meaning the agent will fetch and act on untrusted public web content that could contain instructions influencing its actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's setup instructs users to run the remote installer with "curl -fsSL https://indices.io/install.sh | bash", which fetches and executes remote code and is required before using the skill.