Skills
skills/cinience/alicloud-skills/aliyun-live-manage-test/Gen Agent Trust Hub

aliyun-live-manage-test

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script tests/common/compile_skill_scripts.py to verify the compilation of the target skill.
  • [PROMPT_INJECTION]: The skill ingests data from an external file (skills/media/live/aliyun-live-manage/SKILL.md) to dynamically determine which API operations to execute, creating a surface for indirect prompt injection.
  • Ingestion points: skills/media/live/aliyun-live-manage/SKILL.md referenced in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: python3 command execution and filesystem writes to the output/ directory.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 12:48 PM
Security Audit — agent-trust-hub — aliyun-live-manage-test