The Agent Skills Directory

[SAFE]: The skill provides instructional markdown for API contract design. It does not contain scripts, binaries, or references to external tools that could perform unauthorized actions.
[INDIRECT_PROMPT_INJECTION]: The skill is intended to process external task requirements for design work. However, the lack of tool access, network capabilities, or file system write permissions makes it resilient to exploitation via malicious input.
[METADATA_POISONING]: The frontmatter metadata contains a reference to an unknown model version ('gpt-5.6-sol'), which appears to be a placeholder or platform-specific configuration rather than an attempt to deceive users or bypass security controls.

api-designer