The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes user-provided rough prompts to rewrite them, creating a surface for indirect prompt injection where malicious input could attempt to influence the agent's output logic. * Ingestion points: The skill accepts user-supplied rough or confusing prompts as input (SKILL.md). * Boundary markers: There are no delimiters or instructions to ignore embedded commands within the processed input. * Capability inventory: The skill has no dangerous capabilities such as file system access, network operations, or shell execution. * Sanitization: No sanitization, escaping, or validation of the untrusted input is mentioned.
[NO_CODE]: This skill consists entirely of natural language instructions and does not include any scripts, binaries, or command executions.

sharpen-auto