The Agent Skills Directory

[SAFE]: No malicious code, obfuscation, or unauthorized data exfiltration patterns were detected in the skill instructions.
[EXTERNAL_DOWNLOADS]: The skill mentions the use of standard libraries python-docx and docx (Node.js). These are well-known packages for Word document automation and do not originate from untrusted sources.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing external document data and templates.
Ingestion points: Untrusted data enters the agent context through the processing of Word documents and templates mentioned in SKILL.md.
Boundary markers: The skill lacks explicit instructions or delimiters to isolate document content from the agent's internal logic.
Capability inventory: The agent has the capability to create, edit, and format documents and generate reports as described in SKILL.md.
Sanitization: There are no mentions of sanitization, validation, or filtering of content ingested from Word files.

word-automation