linkfox-ruiguan-copyright-detection
Warn
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: MEDIUMPERSISTENCECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PERSISTENCE]: The skill's onboarding documentation (references/onboarding.md) provides instructions for the agent or user to modify shell configuration files such as ~/.bashrc and ~/.zshrc to persist the LINKFOX_AGENT_API_KEY environment variable.
- [COMMAND_EXECUTION]: The skill relies on Python scripts (scripts/ruiguan_copyright_detection.py, scripts/onboarding.py, scripts/upload_image.py) to perform network operations and manage local file storage for API results and cache data.
- [DATA_EXFILTRATION]: The scripts/onboarding.py script transmits sensitive user authentication data, including phone numbers and SMS verification codes, to the vendor's authentication server at https://api.linkfox.com.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted image URLs provided as input, creating an attack surface for indirect prompt injection where malicious instructions could be embedded in the data processed by the agent. Ingestion points: imageUrl parameter in SKILL.md. Boundary markers: Not specified. Capability inventory: Network requests and file system writes across scripts. Sanitization: No explicit sanitization or validation of external data sources identified.
Audit Metadata