qinghu-tiktok-social
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve and process external social media content, such as TikTok comments and video descriptions. This creates a surface for indirect prompt injection if the ingested data contains adversarial instructions.
- Ingestion points: Untrusted data enters the agent context through the
tiktok_realtime_video_commentsandtiktok_search_itemstools. - Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following commands embedded in the comments.
- Capability inventory: The skill possesses the capability to perform network requests (
curl,fetch,requests) and interact with file export tools. - Sanitization: No sanitization or filtering logic is specified for the processed external content.
- [CREDENTIALS_UNSAFE]: The skill references the use of
QINGHU_TOKENandQHKIT_TOKEN. It correctly instructs the agent to retrieve these from environment variables or ask the user, ensuring that no sensitive keys are hardcoded in the skill code. - [EXTERNAL_DOWNLOADS]: The skill connects to official API endpoints hosted on
www.iqinghu.com. This network activity is documented, transparent, and essential to the skill's intended functionality for TikTok monitoring.
Audit Metadata