The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains no instructions to bypass safety guidelines, override previous rules, or adopt unrestricted personas. The use of 'IMPORTANT' and 'CRITICAL' terminology is strictly limited to technical animation standards and rendering quality.
[DATA_EXFILTRATION]: No network operations, credential harvesting, or access to sensitive file paths were detected. The skill operates entirely on animation metadata and local project configurations.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts. The skill mentions the standard @remotion/motion-blur package, which is an established dependency in the Remotion ecosystem.
[COMMAND_EXECUTION]: The instructions do not involve the execution of shell commands, system utilities, or administrative tools.
[OBFUSCATION]: The content is presented in clear markdown and code blocks. No Base64, zero-width characters, homoglyphs, or hidden URLs were identified.
[DYNAMIC_EXECUTION]: While the skill provides TypeScript snippets for animation logic, these are intended as static templates for video rendering code. There is no usage of unsafe evaluation, dynamic loading from computed paths, or untrusted deserialization.
[PRIVILEGE_ESCAlATION]: The skill does not request or attempt to acquire elevated permissions or modify system configurations.
[INDIRECT_PROMPT_INJECTION]: The skill processes animation parameters and music maps. It does not ingest untrusted natural language data that could be used to influence agent behavior.

klik-cam