ecommerce-tiktok-creator-analytics
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the TikTok platform via an external API, creating a potential vector for indirect prompt injection through creator profile content.\n
- Ingestion points: Data is retrieved from the Kalodata API and processed by scripts
scripts/creator_detail.pyandscripts/creator_rank.py.\n - Boundary markers: The instructions do not define clear delimiters or provide instructions to the agent to disregard potential commands embedded within external creator data fields like
creator_bioorcreator_nickname.\n - Capability inventory: The associated scripts have permissions to perform network requests (
urllib.request) and write files to the local filesystem (nexscopedata directory).\n - Sanitization: The skill lacks logic to sanitize or filter the API response content to remove potential instruction-based payloads before they are presented to the agent.
Audit Metadata