The Agent Skills Directory

[SAFE]: The skill serves as a technical manual and diagnostic framework for audiovisual production. It does not contain any executable code, scripts, or system-level commands.
[EXTERNAL_DOWNLOADS]: The skill includes numerous links to official product documentation and technical guides from well-known and trusted organizations including Apple, Sony, Shure, RODE, the OBS Project, FFmpeg, and Google (YouTube). These links are purely informational and are intended to provide the user with manufacturer-specific settings and safety limits.
[DATA_EXFILTRATION]: The skill includes explicit instructions to protect user privacy. It mandates that personal media should not be shared or reused without consent and provides guidelines for removing personally identifiable information (PII) such as names, emails, and location data from files before processing.
[NO_CODE]: The entire skill is composed of Markdown and YAML configuration files. There are no Python, JavaScript, or Shell scripts included in the package, which significantly reduces the attack surface.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to analyze untrusted user-provided media (photos, videos, audio), it lacks any computational capabilities (like shell execution or network requests) that could be exploited. Furthermore, it contains explicit instructions to treat external documentation as data and ignore any instructions found within processed media.

studio-lendario