tiktok-marketing
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses well-known services for its automation workflows, including Google Sheets, OpenAI, ElevenLabs, and TikTok. These integrations follow standard industry patterns for marketing automation.
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The automation templates ingest data from external sources to generate scripts, which could be exploited if the source data is untrusted.
- Ingestion points: Data is retrieved from Google Sheets in the 'AI Video Content Pipeline' (Node 2) and file metadata in 'Multi-Platform Publishing' (Node 1) within SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the LLM prompt templates (e.g., Node 3: 'Create a TikTok script for: {idea}').
- Capability inventory: The skill possesses capabilities to generate video content and publish directly to TikTok, Instagram, and YouTube via MCP tools and n8n nodes.
- Sanitization: There is no evidence of input validation or sanitization for the data retrieved from external spreadsheets or file metadata.
Audit Metadata