The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata without any associated scripts or executable components.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate skill definitions. Evidence Chain: (1) Ingestion points: User requests for skill creation in SKILL.md. (2) Boundary markers: None. (3) Capability inventory: No subprocesses, file-write, or network operations are defined across any scripts in this skill. (4) Sanitization: None.
[METADATA_POISONING]: The author field is set to 'Claude Code', which refers to the target platform rather than the repository maintainer 'inbharatai'. This is documented as a descriptive attribution rather than a malicious deception.

skill-creator