The Agent Skills Directory

[SAFE]: The skill operates entirely within the agent's conversational context and does not request access to external tools, network resources, or sensitive system files. The instructions are consistent with the stated purpose of assisting users with interview preparation.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from the user, including resumes and job descriptions. This ingestion point is a potential surface for indirect prompt injection attacks. However, because the skill has no access to sensitive capabilities like shell execution, network exfiltration, or file system modifications, the risk of exploitation is effectively neutralized.

interview-coach