The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses natural instructional language to guide the agent in generating video content prompts. No attempts to override safety guidelines or extract system instructions were found.- [DATA_EXFILTRATION]: The skill does not access sensitive local files or environment variables. Network operations are limited to the vendor's API via the 'infsh' CLI tool.- [REMOTE_CODE_EXECUTION]: No instances of piping remote scripts to shells or executing untrusted code were detected. The skill references markdown-based installation instructions and related skills from the platform's official repository.- [OBFUSCATION]: The content is provided in clear text with no evidence of Base64 encoding, zero-width characters, or other hidden content techniques.- [COMMAND_EXECUTION]: Command execution is scoped to the 'infsh' CLI and standard shell loops for automation within the platform's intended use case. No dangerous system commands or privilege escalation attempts are present.- [INDIRECT_PROMPT_INJECTION]: The skill primarily generates content based on static templates and user-provided descriptions. It does not ingest or process untrusted external data in a way that creates an injection surface.

ai-marketing-videos