The Agent Skills Directory

[SAFE]: No malicious patterns, data exfiltration attempts, or unauthorized command executions were detected. The skill is designed for task-specific content generation using local files.- [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection as it processes data from several local workspace files. However, the risk is minimal because the skill does not possess any dangerous capabilities. 1. Ingestion points: workspace/pages/[page-name]/strategy.json, workspace/brand/profile.md, and workspace/brand/extract.md. 2. Boundary markers: No explicit delimiters or safety instructions are used to isolate ingested data. 3. Capability inventory: The skill performs text generation only and does not include network operations, subprocess calls, or persistent file writes. 4. Sanitization: No content validation or sanitization routines are implemented for the ingested data.

page-copy