The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to run local Python scripts such as scripts/content/generate_sequence.py and scripts/content/analyze_sequences.py. These scripts are part of the skill's internal package and are used for the intended purpose of content generation and pattern analysis.
[PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill reads content from external or user-provided email examples in the references/ directory.
Ingestion points: Reads files from the references/examples/emails/ directory.
Boundary markers: No specific boundary markers or 'ignore' instructions are defined to separate the processed data from the agent's instructions.
Capability inventory: The skill has Write access to the output/ directory and can execute local scripts via Bash.
Sanitization: The skill does not explicitly describe any sanitization or filtering processes for the data read from the reference files.

nurture-sequence