ads-tiktok
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION] (SAFE): No instructions were found that attempt to bypass safety filters, extract system prompts, or override agent constraints. The content is strictly instructional and task-oriented.
- [DATA_EXFILTRATION] (SAFE): There are no network requests, hardcoded credentials, or access patterns targeting sensitive local configuration files (e.g., .ssh or .aws).
- [REMOTE_CODE_EXECUTION] (SAFE): The skill does not perform any external downloads, package installations, or dynamic code execution. It relies on local documentation for its logic.
- [COMMAND_EXECUTION] (SAFE): No shell commands, subprocess calls, or system-level modifications are present in the provided skill.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to ingest TikTok Ads Manager exports. While this represents an external data entry point (Ingestion: TikTok Ads data), the skill has no dangerous capabilities (Inventory: None) to be exploited. There are no boundary markers or sanitization mentioned, but the risk remains low due to the lack of exploitable tools.
Audit Metadata