The Agent Skills Directory

[Prompt Injection] (SAFE): No override markers, role-play injections, or attempts to bypass safety filters were found in the text.- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths (like ~/.ssh or .env), or unauthorized network operations were identified.- [Unverifiable Dependencies] (SAFE): The skill does not perform any package installations (npm, pip) or remote script executions. References to FFmpeg are conceptual guidelines for the agent's behavior.- [Indirect Prompt Injection] (LOW): While the skill involves processing video metadata (an untrusted data source), it lacks the specific code or capability to execute instructions contained within that metadata.- [Obfuscation] (SAFE): No Base64, zero-width characters, homoglyphs, or other encoding techniques were used to hide malicious intent.- [No Code] (SAFE): This skill is entirely comprised of markdown instructions and does not include any accompanying scripts or executables.

video-engineer