The Agent Skills Directory

[SAFE]: The automated scanner's detection of SKILL.md as malicious is a false positive. A manual audit of the file confirms it contains only instructional markdown and configuration examples for agent development, with no evidence of malicious code, hidden payloads, or harmful scripts.
[COMMAND_EXECUTION]: The skill provides Python scripts (scripts/init_skill.py, scripts/package_skill.py) that automate local file system tasks such as directory creation, template generation, and ZIP archiving. These operations are performed using standard libraries and are consistent with the skill's purpose as a developer utility.
[DYNAMIC_EXECUTION]: The quick_validate.py script uses the yaml.safe_load function to process YAML metadata. This is a secure implementation that prevents arbitrary code execution during the parsing of configuration files.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided task descriptions to generate instructions for other AI agents. While this capability presents a surface for indirect prompt injection, the skill does not possess sensitive data access or network capabilities that would allow for exploitation or exfiltration, resulting in a safe environment.

skill-creator