The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions and test cases in JSON format. It does not include any scripts, executable binaries, or system-level commands.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user input based on specific triggers related to investment scenarios. While this creates an ingestion point for untrusted data, the skill's capabilities are restricted to natural language guidance and evaluation. It lacks any high-risk capabilities such as file system writing, network requests, or code execution that could be exploited through data-driven instructions.
[REMOTE_CODE_EXECUTION]: No patterns for remote code execution, such as curl-to-bash or package installations, were detected in the skill files.

capability-circle