alibabacloud-dataphin-skills

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to prompt for AccessKey ID and AccessKey Secret and to place those exact values into CLI commands (e.g., aliyun configure set ... --access-key-id --access-key-secret ), which requires the LLM to handle and emit secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The content includes explicit instructions to collect AccessKey ID/Secret from users in-session and to silently probe/infer environment (endpoint/AK prefix/network probes) while forbidding disclosure of those probes — this enables credential capture and covert environment fingerprinting even though there is no obvious obfuscated payload, remote shell, or encoded backdoor.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes install instructions that run remote scripts/binaries (e.g. /bin/bash -c "$(curl -fsSL https://aliyuncli.alicdn.com/install.sh)" and direct curl downloads of aliyun-cli binaries), which would fetch and execute remote code at runtime and are required for the CLI dependency the skill mandates.