officecli-accessibility
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill identifies a dependency on the officecli tool and provides a link to the author's official GitHub repository (https://github.com/lidge-jun/OfficeCLI). The instructions follow security best practices by requesting user consent and checking for existing installations instead of automated execution.
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it is designed to read and process content from potentially untrusted Office documents.
- Ingestion points: Document data is ingested via officecli query, get, and view commands in SKILL.md.
- Boundary markers: No delimiters or instructions are present to help the agent distinguish between document content and its own operating instructions.
- Capability inventory: The skill has the ability to read, modify, and move file content using officecli set, move, and batch commands.
- Sanitization: There is no evidence of content validation or sanitization before the document data is processed by the agent.
Audit Metadata