tiktok-research
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external platform (TikTok) which creates a risk for indirect prompt injection attacks where malicious instructions embedded in video descriptions, comments, or creator profiles could attempt to influence the agent's behavior.
- Ingestion points: The skill ingests data through various tools including
tiktok_app_v3_general_search_result,tiktok_app_v3_creator_info,tiktok_app_v3_one_video, andtiktok_app_v3_live_room_info(identified in SKILL.md and references/sandbase-api-map.md). - Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted tool outputs from the agent's system instructions.
- Capability inventory: The skill utilizes
sandbase_call_toolto interact with the SandBase API for data retrieval and research. - Sanitization: The skill does not specify any sanitization, filtering, or validation steps for the content retrieved from TikTok before processing.
Audit Metadata