The Agent Skills Directory

[SAFE]: The skill contains no prompt injections, credential exposures, persistence mechanisms, or malicious command execution patterns. All instructions and scripts are consistent with the stated purpose of recruitment operations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, such as candidate resumes and talent profiles, which creates a theoretical injection surface. However, the risk is mitigated as there are no dangerous capabilities available to the agent for exploitation.
Ingestion points: Processes resume content from various ATS platforms and recruitment datasets (SKILL.md).
Boundary markers: Absent; the skill does not specify delimiters or guardrails for external content.
Capability inventory: No dangerous capabilities such as network operations, file writing, or subprocess execution are present in the instructions or the included Python code.
Sanitization: Absent; the skill does not define specific sanitization or filtering logic for external inputs.
[DYNAMIC_EXECUTION]: The skill includes a Python class, RecruitmentFunnelAnalyzer, used for computing recruitment metrics. The code follows best practices, performing only standard mathematical calculations and data filtering without using unsafe functions like eval() or exec().

Recruitment Specialist