The Agent Skills Directory

[SAFE]: The skill serves as a guide for drafting recommendation letters based on user inputs. It contains no executable scripts, external dependencies, or instructions that bypass safety filters.- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting user-provided data about a candidate's strengths and roles. While it processes untrusted input, it lacks any dangerous capabilities such as network access, command execution, or file system modifications that could be exploited via injection. * Ingestion points: User-supplied candidate details and relationship descriptions. * Boundary markers: Not present. * Capability inventory: None; the skill is purely instructional and does not use tools. * Sanitization: Not present.

reference-letter