The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on a bundled Python script (scripts/md_analysis_planner.py) to process user-provided simulation parameters. Technical review of the script confirms it uses standard argparse for CLI handling and includes explicit constraints on input size (e.g., MAX_SYSTEM_LEN = 256, MAX_GOALS = 64) to prevent resource exhaustion or buffer-related issues.
[DATA_EXFILTRATION]: The analysis confirms the absence of any network-enabled functions, such as curl, requests, or socket operations. The script operates entirely on inputs provided at runtime and does not access sensitive system files or environment variables.
[PROMPT_INJECTION]: The instructions in SKILL.md are focused on domain-specific scientific guidance (e.g., Yeh-Hummer corrections, equilibration checks). No patterns attempting to override agent behavior, bypass safety filters, or extract system prompts were detected.
[REMOTE_CODE_EXECUTION]: The skill contains no external dependencies and does not download or execute remote scripts. It avoids dangerous Python primitives such as eval(), exec(), or os.system().

md-analysis-planner