Public SkillWarnings

docx

anthropics

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Security Summary

This skill includes a SKILL.md descriptor and ships with scripts. Security observations: behavioral scan truncated and references external URL.

Source

GitHub

Last Scanned

May 1, 2026

License

Proprietary. LICENSE.txt has complete terms

Evidence Index

Category

security

Behavioral scan truncated

Vettd core

scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd exceeds 100KB — content past that limit was not scanned for behavioral signals

warn

References external URL — review for indirect prompt injection risk

Vettd coreOWASP LLM03

External URL(s) detected in SKILL.md — referenced content can change after audit

warn

No prompt injection or jailbreak signals detected

Vettd core

Scanned text content for instruction override, jailbreak framing, credential solicitation, and embedded injection markers

pass

No secrets or unsafe code patterns detected

Vettd core

Scanned all files for credentials, private keys, and code-level risks (eval, shell exec, destructive ops)

pass

Category

best practices

SKILL.md exceeds 500 lines

Vettd core

585 lines — consider moving detailed reference material to references/

warn

Examples included

Vettd core

Found code blocks, input/output samples, or an examples section — concrete samples help agents pattern-match effectively

pass

Progressive disclosure used

Vettd core

SKILL.md body references files in references/, scripts/, or assets/ — agents can load additional context on demand instead of consuming everything upfront

pass

Step-by-step workflow found

Vettd core

Structured procedures improve reliability for complex tasks

pass

Validation loop referenced

Vettd core

Instructions for the agent to validate its own work before proceeding

pass

Category

description

Description includes usage context

Vettd core

Good: description explains when to activate the skill

pass

Description within character limit

Vettd core

785/1024 characters used

pass

Category

evals

No evaluation test cases

Vettd core

Add an evals/ directory with test prompts and expected outputs to measure skill quality

warn

Category