The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access methods were detected. The skill is composed of purely instructional content intended for profile analysis and content generation.
[NO_CODE]: The skill does not include any scripts, executables, or external dependencies, significantly reducing the potential attack surface.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user data such as Instagram bios and posts. Ingestion points: User-provided text or images for profile analysis in SKILL.md. Boundary markers: Absent. Capability inventory: None; the skill does not use any tools or scripts with shell, network, or file system access. Sanitization: Absent. This ingestion surface is considered safe due to the complete lack of exploitable capabilities.

perfil