The Agent Skills Directory

[SAFE]: The skill's logic is focused on classification and structural analysis of social media content. No malicious patterns, such as prompt injection or unauthorized command execution, were found in any of the provided files.\n- [SAFE]: All operations are performed on text inputs provided by the user. The skill does not involve any external downloads, network requests to untrusted domains, or sensitive file system access.\n- [SAFE]: While the skill processes user-provided Instagram captions (representing a surface for indirect prompt injection), it lacks the dangerous capabilities required to exploit such a surface. It performs analysis and generates text templates without the ability to execute shell commands or exfiltrate data.

ig-hook-extractor