tiktok-api

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exposes the agent to untrusted data from TikTok (e.g., video comments and profile bios) which could potentially contain malicious instructions. Ingestion points: Data is retrieved from endpoints like /api/post/search and /api/post/{id}/comments as documented in references/endpoints.md. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present. Capability inventory: The agent can make HTTP GET requests to external APIs. Sanitization: The skill does not describe any sanitization processes for the external data.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the vendor's API at tiktok.fetcher.sh. These network operations are necessary for the skill's primary function and are conducted with the vendor's own infrastructure.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill uses safe placeholders for API keys in documentation and examples, and correctly advises users to manage credentials via environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 07:35 PM
Security Audit — agent-trust-hub — tiktok-api