The Agent Skills Directory

[SAFE]: The skill instructions and associated scripts do not exhibit any malicious patterns. The workflow is focused on documentation generation and uses a deterministic verification script to ensure all required metadata fields are filled by the user.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local Python script (scripts/check_model_card_complete.py) for linting markdown documentation. This script uses only standard libraries (argparse, json, re, pathlib) and does not perform any dangerous operations such as arbitrary command execution, network requests, or sensitive file access.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data (user-supplied model facts) and writing them to files. However, it implements safety boundaries through explicit anti-hallucination instructions, template-based structures with [NEEDS INPUT] markers, and a validation script that flags empty placeholders. The risk is managed and consistent with the skill's intended purpose.

model-card