The Agent Skills Directory

[SAFE]: The skill does not perform any network operations, file system modifications, or command executions. Its functionality is restricted to text processing and analysis within the agent's context.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompt text to provide feedback and rephrased versions. This constitutes an ingestion point for untrusted data (Ingestion points: SKILL.md 'Entradas'). While the instructions do not define specific structural boundary markers for the input (Boundary markers: absent), the skill has no external capabilities or tool access that could be exploited (Capability inventory: none). Furthermore, it includes mandatory instructions to redact sensitive information found in the input (Sanitization: secret masking with [REDACTED]).
[CREDENTIALS_SAFE]: The skill implements a security policy that specifically instructs the agent to identify and redact sensitive credentials such as API keys, tokens, and passwords, replacing them with a redacted placeholder to prevent accidental exposure.

prompt-validate