The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or security vulnerabilities were identified in the skill instructions.
[NO_CODE]: The skill consists entirely of natural language instructions and does not include any scripts, executables, or third-party dependencies.
[PROMPT_INJECTION]: The skill processes user-provided prompts for minification. Although this creates a surface for indirect prompt injection, the agent has no tools, network access, or system-level capabilities to exploit. * Ingestion points: User input defined in SKILL.md. * Boundary markers: Absent. * Capability inventory: None. * Sanitization: Absent.

prompt-minifier