The Agent Skills Directory

[SAFE]: The skill is a utility for literary analysis. Its script performs local text processing and does not invoke network tools, access sensitive files, or execute arbitrary system commands.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied stories and scripts, creating a surface for potential indirect prompt injection. However, since the skill has no high-risk capabilities (network, file system, or code execution) and includes specific constraints for analysis quality, the risk is considered safe.\n
Ingestion points: The input_text argument in the execute_workflow method within scripts/drama_workflow.py.\n
Boundary markers: No explicit delimiters or instructions are used to isolate user content.\n
Capability inventory: Local text splitting, truncation, and result integration; no network or shell execution capabilities.\n
Sanitization: Input text is processed as-is without sanitization.

drama-workflow