itut-drafting
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process, edit, and format ITU-T documents (.docx) using the
officeclitool. This creates a surface for indirect prompt injection where an adversary could embed malicious instructions within a document's text or metadata to influence the agent's behavior during the drafting process. - Ingestion points: The skill ingests content from Word templates and user-provided documents (e.g.,
assets/template.docx). - Boundary markers: The instructions do not specify strict delimiters or "ignore instructions" prompts for the content read from the documents.
- Capability inventory: The skill uses
officeclito perform complex document operations, includingraw-setfor XML injection and batch updates. - Sanitization: There is no explicit sanitization of the text content extracted from the documents before it is processed by the agent.
Audit Metadata