The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user prompts for refinement in SKILL.md. There are no specific boundary markers or instructions to ignore embedded commands within the input. While the skill mentions using available tools for context, it contains a strict prohibition against writing or executing code, which limits the risk of the agent performing harmful actions based on the processed data. No sanitization or validation of the input content is specified.
[SAFE]: No indicators of malicious activity such as data exfiltration, credential theft, or obfuscation were detected.

boost-prompt