office-export-pdf
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a shell command to perform document conversion using the LibreOffice Kit CLI. The instructions correctly mandate quoting both input and output paths, which mitigates potential command injection risks from maliciously named files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external Office documents, creating a potential surface for indirect prompt injection where instructions hidden within a document could attempt to influence the agent's behavior.
- Ingestion points: Reads content from a user-provided Office document (
<final-office-file>) during the conversion process inSKILL.md. - Boundary markers: No explicit delimiters are used for the file content, which is standard for binary/complex Office document processing.
- Capability inventory: The skill has the ability to execute shell commands via a Node.js CLI and write files to the workspace as defined in
SKILL.md. - Sanitization: Employs argument quoting for file paths to prevent shell-level injection in
SKILL.md.
Audit Metadata