douyin-hotlist-overall
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python runner script (scripts/run.py) that facilitates communication with an external API using standard Python libraries for JSON and HTTP processing.
- [EXTERNAL_DOWNLOADS]: The skill initiates network requests to the vendor's API at https://ai-skills.ai. This domain belongs to the skill's author and serves as the infrastructure for the skill's functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for potential indirect prompt injection as it retrieves real-time trending topics from the Douyin platform.
- Ingestion points: Data is fetched from an external API via network requests in scripts/run.py.
- Boundary markers: The script returns data as structured JSON; no specific boundary markers for LLM consumption are implemented in the runner script.
- Capability inventory: The script possesses network access to the vendor's API but does not include file-writing or system-modifying capabilities.
- Sanitization: The script validates JSON structure but does not filter or sanitize the strings within the retrieved trending topics.
Audit Metadata