The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or security vulnerabilities were detected. The skill consists entirely of instructional markdown and reference text providing hiring advice.
[PROMPT_INJECTION]: The instructions in SKILL.md are standard agent directives focused on candidate evaluation and do not contain patterns to bypass safety filters or override system prompts.
[DATA_EXFILTRATION]: No hardcoded credentials, sensitive file paths, or network exfiltration patterns were found.
[REMOTE_CODE_EXECUTION]: The skill does not perform any external downloads or execute remote scripts.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for processing untrusted data (Ingestion points: resumes and work samples referenced in SKILL.md). Boundary markers: Absent. Capability inventory: No tool usage, subprocess calls, or network operations are present across the skill files. Sanitization: Absent. Because the skill lacks any dangerous capabilities to exploit, the indirect injection surface poses no security risk.

evaluating-candidates