The Agent Skills Directory

SAFE (SAFE): The skill consists entirely of informational Markdown documents and formatting templates. Evidence: SKILL.md, references/platforms.md, references/post-templates.md, and references/reverse-engineering.md contain only text-based instructions and do not include any executable code, scripts, or binary files.
Indirect Prompt Injection (SAFE): The 'Reverse Engineering' framework in references/reverse-engineering.md describes a workflow for analyzing external social media content. While this represents a theoretical ingestion surface for untrusted data, the skill lacks any automated scripts or tools to process this data directly.
Ingestion points: Social media post content (text, hooks, CTAs) from external platforms.
Boundary markers: None (the workflow is described as a manual or third-party tool-assisted process).
Capability inventory: None (no scripts or executable files are included in the skill).
Sanitization: Not applicable.
Data Exposure & Exfiltration (SAFE): The skill references a local context file (.claude/product-marketing-context.md). This is a standard practice for providing domain-specific background in the intended environment and does not involve accessing sensitive system files or hardcoded credentials.

social-content