The Agent Skills Directory

[SAFE]: The skill is composed entirely of informational Markdown files, including guides, templates, and research summaries. No executable scripts (.py, .js, .sh) or configuration files that could trigger automated commands were found.
[EXTERNAL_DOWNLOADS]: The skill identifies and recommends various third-party tools for software forecasting (e.g., mcprojsim, ScopeCone, Kitmul, Monte.one). These are presented as resources for the user to evaluate and utilize manually, rather than being fetched or executed by the agent itself. The inclusion of pip install mcprojsim is provided as an instructional example for users wanting CLI integration.
[COMMAND_EXECUTION]: While the skill contains shell command examples (e.g., mcprojsim --throughput ...), these are documentation snippets for the user. No dynamic context injection patterns (such as !command) or automated command execution logic were detected in the skill's instructions.
[DATA_EXFILTRATION]: No attempts to access sensitive system files (e.g., SSH keys, AWS credentials, environment variables) or hardcoded secrets were detected. Network operations are limited to referencing documentation and tool websites.
[PROMPT_INJECTION]: The skill uses instructional directives to define its scope (e.g., 'Do NOT invoke for...'), which are standard for guiding agent behavior and do not attempt to bypass safety filters or override system-level constraints.

estimation-weapon