alibabacloud-aisc-skill-inspection

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a Python wrapper script (scripts/skill_file_check.py) to interface with the Alibaba Cloud AISC API. It executes standard CLI subcommands (submit, poll, run) to manage security scanning tasks.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with official Alibaba Cloud API endpoints (aisc.cn-shanghai.aliyuncs.com) to submit scanning requests and retrieve results. This is normal functionality for a cloud-connected tool.
  • [SAFE]: The instructions include robust safety constraints that explicitly prohibit the agent from downloading or probing user-provided URLs locally using tools like curl or wget. This design effectively mitigates Server-Side Request Forgery (SSRF) and local execution risks by ensuring that potentially malicious files are only handled by the remote AISC scanning service.
  • [SAFE]: The skill uses the official alibabacloud_credentials SDK to handle authentication, ensuring that credentials are managed via the standard provider chain rather than being hardcoded or exposed in logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 01:59 AM
Security Audit — agent-trust-hub — alibabacloud-aisc-skill-inspection