alicloud-ai-recommend-airec-test
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (
tests/common/compile_skill_scripts.py) to verify skill compilation. - [PROMPT_INJECTION]: The skill processes the content of an external
SKILL.mdfile to identify API endpoints to test, which presents an indirect prompt injection surface. - Ingestion points:
SKILL.mdfrom the target recommendation skill path. - Boundary markers: Absent.
- Capability inventory: Local command execution and cloud API calls.
- Sanitization: No sanitization or validation of the ingested markdown content is described.
Audit Metadata