The Agent Skills Directory

[SAFE]: The skill operates as a text-based decision matrix. It ingests user descriptions via the $ARGUMENTS variable to match against a static table of QA scenarios.
[DATA_EXPOSURE]: The skill frontmatter explicitly states that no network access is required, and the instructions confirm it only provides text recommendations based on internal logic.
[INDIRECT_PROMPT_INJECTION]: While the skill processes untrusted user input ($ARGUMENTS) without explicit boundary markers, it possesses no dangerous capabilities (such as shell execution, file system writes, or network requests) that would allow an injection to escalate into a security threat. The output is strictly limited to identifying related skills.

qa-do