The Agent Skills Directory

[SAFE]: No security threats were identified across the 10 monitored categories. The skill is composed entirely of markdown documentation and instructional content.
[NO_CODE]: The skill does not contain any executable scripts, shell commands, or external dependencies, significantly reducing its attack surface.
[PROMPT_INJECTION]: Instructions were reviewed for adversarial patterns such as role-play instructions, safety bypasses, or system prompt extraction; none were found.
[DATA_EXFILTRATION]: No network operations, hardcoded credentials, or access to sensitive local file paths (e.g., .ssh, .aws) were detected.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests context from MEMORY.md and USER.md, it lacks the technical capabilities (tools, code execution) required to exploit these ingestion points.

problem-definition