linkfox-ruiguan-copyright-detection
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses Python scripts (
ruiguan_copyright_detection.py,onboarding.py,upload_image.py) to interact with its backend APIs. These scripts are executed via standard shell commands from the agent environment. - [EXTERNAL_DOWNLOADS]: The
onboarding.pyscript includes logic to download and install theqrcodeandrequestspackages if they are missing from the environment. These are standard, well-known libraries used for generating payment QR codes and handling HTTP requests. - [DATA_EXPOSURE]: The skill accesses the
SESSION_IDandLINKFOX_AGENT_API_KEYenvironment variables to authenticate requests and organize output data. This is standard practice for agent-based tools interacting with authenticated APIs. - [INDIRECT_PROMPT_INJECTION]: The skill processes external image URLs and returns metadata such as similarity scores and rights owner information. While it ingests external data, the output is structured and used for informational purposes with specific guidance that the results do not constitute legal advice, minimizing the risk of prompt injection influencing agent behavior.
Audit Metadata