fucai3d-latest
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to run a local Python script (
recommender.py) to manage lottery history and generate number recommendations. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites (Baidu search results) and uses it to construct shell commands.
- Ingestion points: Data is fetched from Baidu search result pages as specified in SKILL.md steps 1-5.
- Boundary markers: The instructions do not define boundary markers or specify that the agent should ignore instructions embedded within the lottery results.
- Capability inventory: The agent is authorized to execute the
/var/minis/shared/fucai3d/recommender.pyscript via the shell and write to local history files. - Sanitization: There are no instructions for the agent to validate or sanitize the input strings before passing them as command-line arguments, creating a surface for command injection.
Audit Metadata