The Agent Skills Directory

[SAFE]: The skill performs standard resume optimization tasks as described in its documentation. No evidence of obfuscation, credential harvesting, or unauthorized network activity was found.
[COMMAND_EXECUTION]: The skill utilizes MCP tools (extract_text_from_pdf, extract_text_from_docx, create_docx) for document handling, which are appropriate for a resume-focused tool and consistent with the vendor's provided metadata.
[PROMPT_INJECTION]: The skill processes untrusted external data (job descriptions and resumes), creating a surface for indirect prompt injection.
Ingestion points: User-provided text and files processed during the resume analysis step (SKILL.md).
Boundary markers: None explicitly defined to separate user input from internal instructions.
Capability inventory: Document reading and creation capabilities via the office-mcp server.
Sanitization: Relies on default model guardrails; no specific input validation or escaping is present in the skill's instructions.

resume-tailor