The Agent Skills Directory

[SAFE]: No security concerns were identified during the analysis of this skill.
[PROMPT_INJECTION]: The instructions focus entirely on clarifying user intent and formatting output for a video generation model. There are no attempts to override the agent's core instructions or bypass safety filters.
[DATA_EXFILTRATION]: The skill does not perform any network operations, nor does it access sensitive local files or environment variables. All references are to internal documentation within the skill's repository structure.
[REMOTE_CODE_EXECUTION]: No remote scripts are downloaded or executed. The skill does not use any package managers (npm, pip) or dynamic execution functions (eval, exec).
[COMMAND_EXECUTION]: The skill contains no shell commands, subprocess calls, or privilege escalation attempts.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user input, its only capability is to output text prompts. It does not interact with any external APIs or sensitive tools that could be exploited via malicious user input.

seedance-prompter