The Agent Skills Directory

[NO_CODE] (SAFE): The skill is composed exclusively of Markdown files (SKILL.md, patterns.md, validations.md). There are no Python scripts, Node.js packages, shell scripts, or binaries included.
[DATA_EXPOSURE & EXFILTRATION] (SAFE): No sensitive file paths, environment variables, or hardcoded credentials (API keys, tokens) were detected. The skill does not perform any network operations (curl, fetch, etc.).
[REMOTE_CODE_EXECUTION] (SAFE): There are no patterns involving remote script downloads or the execution of external code. No package managers (pip, npm) are invoked.
[PROMPT_INJECTION] (SAFE): The instructions define a specific persona and reference system but do not contain attempts to override safety filters, extract system prompts, or bypass AI constraints.
[INDIRECT PROMPT INJECTION] (LOW): The skill is designed to process and validate user-provided business strategies. While this involves processing untrusted input, the skill lacks any dangerous capabilities (like file system writes or network access) that could be exploited via injection. The risk is limited to the AI providing biased or incorrect advice based on the input.
[COMMAND_EXECUTION] (SAFE): No system commands or subprocess calls are present in the provided files.

growth-strategy