aliyun-cloudauth-verify-test
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script located at
tests/common/compile_skill_scripts.pyto perform an offline compilation check of another skill. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it is instructed to read external content from
skills/security/identity/aliyun-cloudauth-verify/SKILL.mdand use that information to decide which API calls to execute. - Ingestion points: Reads
SKILL.mdfrom the target skill path. - Boundary markers: None; the agent is instructed to read the target file and identify APIs directly.
- Capability inventory: Includes local command execution (
python3) and file system write operations to theoutput/directory. - Sanitization: No validation or sanitization is performed on the instructions or API names extracted from the target skill's documentation.
Audit Metadata