The Agent Skills Directory

[SAFE]: The skill operates entirely within the local environment. It reads internal brand configuration files and writes generated email templates to specified project folders.
[SAFE]: No external network operations, such as curl or wget, are present in the skill instructions or reference files.
[SAFE]: The skill does not include any obfuscated code, Base64 encoding, or hidden characters. All instructions are clear and transparent.
[SAFE]: No unverifiable dependencies or remote script executions are attempted. The skill only references local skills and standard CLI tools for output compatibility.
[PROMPT_INJECTION]: The skill processes content from brand documentation files to influence email generation, creating a surface for indirect prompt injection.
Ingestion points: Reads files from the brand/ directory, including voice-profile.md, audience.md, and positioning.md.
Boundary markers: Absent.
Capability inventory: Performs file-write operations to marketing/emails/ and campaigns/ directories across all scripts.
Sanitization: No explicit sanitization or delimiting of the input brand data is performed before interpolation into the generation context.

email-sequences