The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected. The skill consists of instructional markdown files and configuration data without executable scripts or remote dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill demonstrates an ingestion surface for indirect prompt injection as it reads user-provided context such as brand profiles and voice guidelines to draft social media content. 1. Ingestion points: The skill reads from brand-profile and voice-builder files as specified in SKILL.md. 2. Boundary markers: No explicit delimiters or boundary markers were identified in the instructions. 3. Capability inventory: The skill performs content generation and utilizes external scheduling tools. 4. Sanitization: Significant human-in-the-loop oversight is mandated, with a human required to post live comments, send invites, and review all scheduled content.

linkedin-growth