The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted external documents (resumes and applications) through MCP tools, which creates an attack surface for indirect prompt injection.
Ingestion points: The skill uses extract_text_from_pdf and extract_text_from_docx from the office-mcp server to ingest document content (SKILL.md).
Boundary markers: There are no explicit instructions or delimiters used to warn the agent to ignore potentially malicious instructions embedded within the resumes.
Capability inventory: The skill's capabilities are focused on candidate_evaluation, requirement_matching, and scoring (SKILL.md).
Sanitization: No content sanitization or validation of the ingested text is performed before it is processed by the AI model.

Applicant Screening