viral-youtube-titles
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely text-based and contains no executable scripts, shell commands, or network operations. All instructions are focused on natural language generation and adhering to specific writing constraints.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided information regarding video topics, audiences, and facts (defined in the Input Contract in
SKILL.md) to generate titles. While this is an ingestion surface for potentially malicious data, the skill lacks the capabilities (such as file system access, network requests, or subprocess execution) required for a prompt injection to manifest as a functional security threat. Standard model guardrails handle content safety.
Audit Metadata