spice-cloud-management

[Skill Scanner] Natural language instruction to download and install from URL detected All findings: [CRITICAL] command_injection: Natural language instruction to download and install from URL detected (CI009) [AITech 9.1.4] [HIGH] command_injection: Backtick command substitution detected (CI003) [AITech 9.1.4] This skill's documentation and commands are internally consistent: it legitimately requires a management bearer token and provides curl examples and a local helper script to interact with Spice.ai management endpoints. I found no indicators of obfuscation, credential exfiltration to third-party domains, hardcoded secrets, or other malicious behaviors in the provided text. The principal risk is the normal operational risk of giving a management token to any tool — the helper script should be inspected before execution, because it will have access to the token and could perform privileged actions if malicious. Overall, the content appears benign and consistent with its stated purpose. LLM verification: BENIGN to SUSPICIOUS: The skill description is coherently aligned with its stated purpose and uses standard API patterns. There is no evidence of hidden data flows or credential theft. The only notable concern is a documentation artifact involving backtick token references in a code snippet and a potential misinterpretation of token retrieval flow; these are not actual malware patterns but should be clarified to avoid user confusion. Overall, the footprint is coherent with a legitimate managemen