alicloud-media-mps-test
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (
tests/common/compile_skill_scripts.py) to perform an offline compilation check on the target skill scripts.\n- [PROMPT_INJECTION]: The skill processes external documentation and API response data, which is a surface for indirect prompt injection.\n - Ingestion points: Reads
SKILL.mdfrom the target skill path and processes raw Alibaba Cloud API outputs.\n - Boundary markers: None specified to distinguish between test instructions and data processed from external files or APIs.\n
- Capability inventory: Subprocess execution of local scripts via
python3and network-based API queries.\n - Sanitization: No explicit sanitization or filtering of the ingested skill content or API responses is mentioned.
Audit Metadata