The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not contain any executable code, shell commands, or network operations. It provides structured guidance for the agent to generate comparison tables and recommendations based on user-provided topics.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided topics via the $ARGUMENTS variable. While this is a theoretical attack surface for indirect prompt injection, the skill lacks any impactful capabilities (such as network access, file system modifications, or shell execution) that could be exploited through such an injection. The impact is limited to the generated text response.

learn-alternatives