The Agent Skills Directory

[DYNAMIC_EXECUTION]: The scripts/init_skill.py script generates an executable Python file from a template string when creating new skill directories.\n- [PRIVILEGE_ESCALATION]: The init_skill.py script uses chmod(0o755) to grant executable permissions to the generated boilerplate script, which involves runtime permission modification.\n- [INDIRECT_PROMPT_INJECTION]: The skill functions as a generator for other skills, creating an attack surface where user-provided functionality descriptions are incorporated into generated instructions without explicit sanitization.\n
Ingestion points: User prompts defining new skill functionality and content for SKILL.md.\n
Boundary markers: No delimiters or isolation instructions are provided in the generation templates to handle untrusted user input.\n
Capability inventory: The toolset includes file system creation, file writing, and permission management capabilities.\n
Sanitization: The provided automation scripts do not include mechanisms for sanitizing or validating user input before it is written to the skill files.

skill-creator