The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected. The skill focuses on generating structured markdown documents for recruiting purposes.
[DATA_EXFILTRATION]: The skill does not perform any network operations (e.g., curl, wget, fetch) or attempt to access sensitive files like SSH keys, AWS credentials, or .env files.
[REMOTE_CODE_EXECUTION]: The skill does not install third-party packages, execute shell scripts from remote sources, or use dynamic execution functions like eval() or exec().
[PROMPT_INJECTION]: The instructions follow standard formatting and do not contain directives to bypass AI safety filters, ignore previous instructions, or disclose system prompts.
[INDIRECT_PROMPT_INJECTION]: The skill ingests a <role> parameter from the user.
Ingestion points: The <role> argument is used to populate the filename RECRUIT-INTERVIEW-[Role].md and as a header within the generated content.
Boundary markers: Absent; the role name is directly interpolated.
Capability inventory: The only capability utilized is the creation of a local markdown file.
Sanitization: Not explicitly defined, but the limited scope of the output (a markdown text file) presents no significant security risk.
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or passwords were found in the skill metadata or body.

recruit-interview