tiktok-script-writer
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the web via the
web_searchtool to identify product features and viral trends.\n - Ingestion points: Product research (Step 1) and TikTok trend analysis (Step 1.5) in
SKILL.mdutilizeweb_searchto fetch external content.\n - Boundary markers: The instructions do not include delimiters or specific guidance to ignore embedded instructions within the searched data.\n
- Capability inventory: The skill's primary function is generating formatted text scripts; it does not trigger file-write, network exfiltration, or command execution tools based on the ingested data.\n
- Sanitization: No explicit validation or filtering of search results is performed before interpolation into the script generation process.
Audit Metadata