cli-anything-libreoffice
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection because it processes untrusted content from external documents and user-provided text that could contain malicious instructions for the agent.
- Ingestion points: The skill ingests untrusted data via the
document importcommand and content creation commands such asadd-paragraph,add-heading,add-list,add-table, andset-textas described inSKILL.md. - Boundary markers: The instructions do not specify any boundary markers or delimiters to isolate untrusted content, nor do they instruct the agent to ignore embedded instructions in the data.
- Capability inventory: The skill has the capability to write to the local file system through the
export rendercommand, allowing an attacker to potentially influence file creation or overwrite operations. - Sanitization: There is no evidence of input validation, sanitization, or safety filtering applied to the imported content.
Audit Metadata