The Agent Skills Directory

[PROMPT_INJECTION]: The skill ingests untrusted data from various local files, creating a surface for indirect prompt injection attacks where embedded instructions in data files could influence the agent.
Ingestion points: Data is read from marketing-project.json, content-strategy.json, campaigns/*.json, calendar/content-calendar.yaml, and the content/ directory.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard commands found within these data sources.
Capability inventory: The skill is authorized to use Read, Write, Edit, Bash, Glob, and Grep tools.
Sanitization: No sanitization or validation of the processed data is specified before it is used to generate the dashboard.
[SAFE]: No high-severity patterns such as credential theft, remote code execution, or network exfiltration were found. The generated dashboard is self-contained and avoids the use of external CDNs or dependencies.

marketing-dashboard