alicloud-media-mps-test
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
tests/common/compile_skill_scripts.pyusingpython3to perform an offline compilation check of another skill. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its ingestion of external data.
- Ingestion points: The skill reads
skills/media/mps/alicloud-media-mps/SKILL.mdto identify API endpoints to call. - Boundary markers: No boundary markers or instructions to ignore embedded commands are present when processing the target skill file.
- Capability inventory: The agent has the capability to execute shell commands (
python3) and make network requests to Alibaba Cloud APIs. - Sanitization: No sanitization or validation of the content read from the target
SKILL.mdis performed before the agent uses it to determine its next action.
Audit Metadata