The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs file system operations, specifically reading from and writing to the .agents/redpolitika.md file. These actions are strictly limited to managing project-specific editorial guidelines and are central to the skill's stated purpose.
[EXTERNAL_DOWNLOADS]: The skill contains informational links to the authors' websites (gladlax.ru and niar42.com) for context on editorial practices. There are no automated downloads, script fetches, or remote code execution patterns.
[DATA_EXFILTRATION]: No network operations were found. The skill does not access sensitive system paths or credentials, focusing entirely on user-provided project context.
[PROMPT_INJECTION]: The instructions are focused on structured user interviews and style extraction from provided text samples. No attempts to override safety filters, bypass constraints, or extract system prompts were identified.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text examples to extract stylistic features (sentence length, humor, etc.). While this is an ingestion point for untrusted data, the processing logic is constrained to feature extraction rather than instruction following, and the output is confined to a local markdown template.

redpolitika